# data augmentation

Data augmentation is a machine-learning technique that expands training datasets by applying random or class-preserving transformations to data points.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Improving Outdoor Multi-cell Fingerprinting-based Positioning via Mobile Data Augmentation

DevFeed: [Improving Outdoor Multi-cell Fingerprinting-based Positioning via Mobile Data Augmentation](<https://devfeed.tech/articles/improving-outdoor-multi-cell-fingerprinting-based-positioning-via-mobile-data-augmentation-142498.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2509.19405>)

Author: Tony Chahoud, Lorenzo Mario Amorosa, Riccardo Marini, Luca De Nardis

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [4g lte](<https://devfeed.tech/topics/4g-lte.md>)

Tags: [cellular](<https://devfeed.tech/tags/cellular.md>), [cellular-networks](<https://devfeed.tech/tags/cellular-networks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [drive](<https://devfeed.tech/tags/drive.md>), [error](<https://devfeed.tech/tags/error.md>), [framework](<https://devfeed.tech/tags/framework.md>), [kde](<https://devfeed.tech/tags/kde.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [mobile-data](<https://devfeed.tech/tags/mobile-data.md>), [nearest-neighbor](<https://devfeed.tech/tags/nearest-neighbor.md>), [on-premise](<https://devfeed.tech/tags/on-premise.md>), [outdoor](<https://devfeed.tech/tags/outdoor.md>), [performance](<https://devfeed.tech/tags/performance.md>), [positioning](<https://devfeed.tech/tags/positioning.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [radio](<https://devfeed.tech/tags/radio.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [records](<https://devfeed.tech/tags/records.md>)

### AI overview

The training-free KDE-1NN framework augments operator MDT data by using kernel density estimation to generate geographically coherent locations and a 1-nearest-neighbor block to synthesize per-cell radio fingerprints. Evaluated on real-world data from an Italian mobile operator across urban and peri-urban scenarios, it reportedly improves positioning over state-of-the-art approaches, cutting median error by up to 30% at a 30x augmentation rate in a highly sparse highway scenario. Gains saturate sooner in high-density regions, where additional synthetic samples provide diminishing information. The authors describe the modular approach as interpretable and suitable for distributed or on-premise, privacy-aware operator workflows.

### Source excerpt

arXiv:2509.19405v3 Announce Type: replace-cross Abstract: Accurate outdoor positioning in cellular networks is hindered by sparse, heterogeneous measurement collections and the high cost of exhaustive site surveys. This paper introduces a lightweight, modular mobile data augmentation framework designed to enhance multi-cell fingerprinting-based positioning using operator-collected minimization of drive test (MDT) records. The proposed approach decouples spatial and radio-feature synthesis: kernel density estimation (KDE) models the empirical spatial distribution to generate geographically coherent synthetic locations, while a 1-nearest-neighbor (1NN)-based block produces augmented per-cell radio fingerprints. The architecture is intentionally training-free, interpretable, and suitable for distributed or on-premise operator deployments, supporting privacy-aware workflows. We both validate each augmentation module independently and assess its end-to-end impact on fingerprinting-based positioning using a real-world MDT dataset provided by an Italian mobile network operator across diverse urban and peri-urban scenarios. Results show that the proposed KDE-1NN augmentation consistently improves positioning performance with respect to state-of-the-art approaches, reducing the median positioning error by up to 30% (specifically achieved at an augmentation rate of x30 in the highly sparse highway scenario). We also observe region-dependent saturation effects, which emerge most rapidly in scenarios with high user density where the information gain from additional synthetic samples quickly diminishes. Overall, the framework offers a practical, low-complexity path to enhance operator positioning services using existing mobile data traces.

## FedS2R: One-Shot Federated Domain Generalization for Synthetic-to-Real Semantic Segmentation in Autonomous Driving

DevFeed: [FedS2R: One-Shot Federated Domain Generalization for Synthetic-to-Real Semantic Segmentation in Autonomous Driving](<https://devfeed.tech/articles/feds2r-one-shot-federated-domain-generalization-for-synthetic-to-real-semantic-segmentation-in-autonomous-driving-142496.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2507.19881>)

Author: Tao Lian, Jose L. G\\'omez, Antonio M. L\\'opez

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [autonomous vehicles](<https://devfeed.tech/topics/autonomous-vehicles.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>)

Tags: [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [knowledge-distillation](<https://devfeed.tech/tags/knowledge-distillation.md>)

### AI overview

FedS2R targets synthetic-to-real semantic segmentation for autonomous driving while keeping client data local. It combines inconsistency-driven augmentation to generate images for unstable classes with multi-client knowledge distillation and feature fusion to build a global model from client models in a one-shot federated setting. On Cityscapes, BDD100K, Mapillary, IDD, and ACDC, the global model reportedly outperforms individual client models and comes within 2 mIoU points of a model trained with simultaneous access to all client data.

### Source excerpt

arXiv:2507.19881v4 Announce Type: replace-cross Abstract: Federated domain generalization has shown promising progress in image classification by enabling collaborative training across multiple clients without sharing raw data. However, its potential in the semantic segmentation of autonomous driving remains underexplored. In this paper, we propose FedS2R, the first one-shot federated domain generalization framework for synthetic-to-real semantic segmentation in autonomous driving. FedS2R comprises two components: an inconsistency-driven data augmentation strategy that generates images for unstable classes, and a multi-client knowledge distillation scheme with feature fusion that distills a global model from multiple client models. Experiments on five real-world datasets, Cityscapes, BDD100K, Mapillary, IDD, and ACDC, show that the global model significantly outperforms individual client models and is only 2 mIoU points behind the model trained with simultaneous access to all client data. These results demonstrate the effectiveness of FedS2R in synthetic-to-real semantic segmentation for autonomous driving under federated learning

## Cross-Vehicle Transferability of Lateral Velocity Estimation on Production Vehicles through Input Selection and Data Augmentation

DevFeed: [Cross-Vehicle Transferability of Lateral Velocity Estimation on Production Vehicles through Input Selection and Data Augmentation](<https://devfeed.tech/articles/cross-vehicle-transferability-of-lateral-velocity-estimation-on-production-vehicles-through-input-selection-and-data-augmentation-143554.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24747>)

Author: Hendrik Sch\\"afke, Simon F. G. Ehlers, Thomas Seel, Askar Vagapov, Christoph Schweers, Ahmed Trabelsi, Daniel O. M. Weber

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [enhancing AI model accuracy](<https://devfeed.tech/topics/enhancing-ai-model-accuracy.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [accelerometer](<https://devfeed.tech/tags/accelerometer.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [bias](<https://devfeed.tech/tags/bias.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [car](<https://devfeed.tech/tags/car.md>), [combined](<https://devfeed.tech/tags/combined.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [data](<https://devfeed.tech/tags/data.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [input](<https://devfeed.tech/tags/input.md>), [lateral](<https://devfeed.tech/tags/lateral.md>), [production](<https://devfeed.tech/tags/production.md>), [selection](<https://devfeed.tech/tags/selection.md>), [vehicle](<https://devfeed.tech/tags/vehicle.md>), [vehicles](<https://devfeed.tech/tags/vehicles.md>), [velocity](<https://devfeed.tech/tags/velocity.md>)

### AI overview

A neural network trained on a compact car transfers poorly to an SUV and van: its lateral-velocity estimation error on the unseen vehicles is an order of magnitude higher than on the training vehicle. Comparing inputs drawn from ten production CAN signals identified a five-signal set with the most robust transfer. Of three physically motivated data augmentations, exploiting left-right vehicle symmetry and emulating accelerometer bias improved generalization; together they reduced error on validation maneuvers by 13% for the SUV and 15% for the van. On the SUV, the augmented network matched a model-based estimator tuned on the same training data. The findings are based on real-world drives of three production vehicles and zero-shot evaluation against a GNSS-aided inertial reference.

### Source excerpt

arXiv:2611.24747v1 Announce Type: cross Abstract: Lateral velocity is safety-critical for vehicle-dynamics control but cannot be measured with production sensors. Model-based estimators such as Kalman filters are established, whereas data-driven estimators are more accurate within the training regime but suspected to lose accuracy beyond it. Their transfer to a structurally different vehicle has rarely been tested. We record real-world test drives of three series-production vehicles, train a neural-network estimator on production CAN signals of a compact car, and evaluate it zero-shot on an SUV and a van against a GNSS-aided inertial reference. On the unseen vehicles, the network's error exceeds that on the training vehicle by an order of magnitude, a gap not quantified on production vehicles before. A systematic comparison of input sets from ten production CAN signals identifies a five-signal set that transfers most robustly. To narrow this gap, we introduce three physically motivated augmentations of training data. Two improve generalization, namely exploiting the vehicle's left-right symmetry and emulating accelerometer bias. Combined, they reduce the error on the validation maneuvers of the SUV and van by 13% and 15%. Contrary to common expectation, on the SUV the data-driven estimator trained with both augmentations matches a model-based estimator tuned on the same training data.

## Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation

DevFeed: [Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation](<https://devfeed.tech/articles/pose6daug-physically-plausible-multi-view-object-swapping-for-robot-data-augmentation-143277.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.20118>)

Author: Jonghoon Lee, Seong Hyeon Park, Byungwoo Jeon, Minha Lee, Jinwoo Shin

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [3D](<https://devfeed.tech/topics/3d.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>)

Tags: [2d](<https://devfeed.tech/tags/2d.md>), [3d](<https://devfeed.tech/tags/3d.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [camera](<https://devfeed.tech/tags/camera.md>), [coherent](<https://devfeed.tech/tags/coherent.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [data](<https://devfeed.tech/tags/data.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [data-collection](<https://devfeed.tech/tags/data-collection.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [failure](<https://devfeed.tech/tags/failure.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [manipulation](<https://devfeed.tech/tags/manipulation.md>), [mesh](<https://devfeed.tech/tags/mesh.md>), [object](<https://devfeed.tech/tags/object.md>), [performance](<https://devfeed.tech/tags/performance.md>), [plausible](<https://devfeed.tech/tags/plausible.md>), [policies](<https://devfeed.tech/tags/policies.md>), [robot](<https://devfeed.tech/tags/robot.md>)

### AI overview

Pose6DAug creates targeted demonstrations for VLA policy failure cases by swapping the manipulated object in existing successful episodes while preserving their action trajectories. It anchors the replacement object with a mesh and temporally coherent 6D pose trajectory in 3D, enabling geometrically consistent renderings across calibrated camera views. This addresses multi-view inconsistency and implausible edits that can arise from naive 2D video editing, especially with heavy occlusion and egocentric views. The abstract reports a 16.5% success-rate improvement over the state-of-the-art baseline on novel objects while preserving in-distribution performance; on a real robot, success more than doubled relative to the base policy. These are abstract-level claims; the supplied text gives no further experimental details.

### Source excerpt

arXiv:2606.20118v3 Announce Type: replace-cross Abstract: Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution. The standard remedy is to collect multi-view teleoperation data for every failure case, but this scales poorly in both cost and time. We introduce Pose6DAug, a failure-driven data augmentation framework that turns existing successful episodes into targeted demonstrations for a policy's failure modes, without any new data collection. Our key insight is that each successful episode already encodes a physically valid action trajectory together with calibrated multi-view observations. By swapping only the manipulated object while preserving this trajectory, we obtain new and physically grounded demonstrations. However, the challenge lies in synthesizing object swaps, e.g., naive 2D video editing breaks multi-view consistency and physical plausibility, particularly under heavy occlusion and egocentric viewpoints. Our method instead operates directly in 3D, anchoring the target object with an explicit mesh driven by a temporally coherent 6D pose trajectory. This ensures geometrically consistent renderings across all camera views. Fine-tuning a VLA on data augmented by our method improves success rates by 16.5% relative to the state-of-the-art baseline on novel objects, while preserving in-distribution performance. On a real robot, it more than doubles the success rate of the base policy. These results show that multi-view and physically consistent augmentation is a practical path to scalable VLA generalization.

## Network Intrusion Detection Adaptability under Spurious Labels: A Noise-Aware Few-Shot Class-Incremental Learning Framework

DevFeed: [Network Intrusion Detection Adaptability under Spurious Labels: A Noise-Aware Few-Shot Class-Incremental Learning Framework](<https://devfeed.tech/articles/network-intrusion-detection-adaptability-under-spurious-labels-a-noise-aware-few-shot-class-incremental-learning-framework-137037.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21473>)

Author: Zijian Zhao, Davide Di Monda, Domenico Ciuonzo, Yipeng Wang, Antonio Pescap\\\`e

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>), [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [few-shot-learning](<https://devfeed.tech/topics/few-shot-learning.md>), [few-shot](<https://devfeed.tech/topics/few-shot.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [detection](<https://devfeed.tech/tags/detection.md>), [edge](<https://devfeed.tech/tags/edge.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [framework](<https://devfeed.tech/tags/framework.md>), [iiot](<https://devfeed.tech/tags/iiot.md>), [incremental](<https://devfeed.tech/tags/incremental.md>), [intrusion-detection](<https://devfeed.tech/tags/intrusion-detection.md>), [iot](<https://devfeed.tech/tags/iot.md>), [logistic-regression](<https://devfeed.tech/tags/logistic-regression.md>), [memory](<https://devfeed.tech/tags/memory.md>), [nearest-neighbor](<https://devfeed.tech/tags/nearest-neighbor.md>), [network](<https://devfeed.tech/tags/network.md>), [network-traffic](<https://devfeed.tech/tags/network-traffic.md>), [noise](<https://devfeed.tech/tags/noise.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [statistics](<https://devfeed.tech/tags/statistics.md>)

### AI overview

NAFN aims to make few-shot class-incremental network intrusion detection more resilient to mislabeled examples in newly observed attack classes. It detects and removes suspected mislabeled biflows, then estimates class-conditional embeddings from the remaining clean data, calibrates them with base-class statistics, and resamples synthetic features to restore the original biflow count. The framework uses the Rethink Few-Shot teacher-student paradigm with nearest-neighbor or logistic regression classifiers and different pretraining and memory-selection strategies. On CSE-CIC-IDS2018, Edge-IIoT, and IoT-NID, the abstract reports retained prior knowledge and strong incremental performance with up to 50% label noise; new-class F1 improved over non-denoised baselines by as much as 52%. It also reports time efficiency and robustness across networks and high-noise settings.

### Source excerpt

arXiv:2611.21473v1 Announce Type: new Abstract: Network Intrusion Detection Systems (NIDSs) must incrementally adapt to emerging attacks, even when only a limited amount of labeled network traffic is available. Consequently, Few-Shot Class-Incremental Learning (FSCIL)-based NIDSs have gained growing attention. However, existing FSCIL-based NIDSs are highly vulnerable to label noise in newly-observed attack classes. To address this limitation, we propose NAFN, a noise-aware FSCIL-based NIDS framework that reduces the impact of mislabeled data during incremental adaptation. NAFN consists of two components: (i) Noise Detection, which identifies and removes mislabeled biflows using noise-detection algorithms, and (ii) Feature Sampling, which estimates class-conditional embeddings from clean biflows, calibrates them with base-class statistics, and resamples synthetic features to recover the original biflow count. The framework follows the Rethink Few-Shot (RFS) teacher-student paradigm with lightweight nearest-neighbor or logistic regression classifiers, and various pretraining & memory selection strategies. Experiments on CSE-CIC-IDS2018, Edge-IIoT, and IoT-NID datasets show that NAFN effectively preserves prior knowledge and maintains strong incremental performance even under 50% label noise, consistently improving new-class F1-scores over non-denoised baselines, up to +52%, while being time-efficient and robust in cross-network and high-noise incremental settings. The implementation is publicly available to foster reproducibility.

## Symmetry Fingerprinting with Geometric Learnable Invariants Transformers

DevFeed: [Symmetry Fingerprinting with Geometric Learnable Invariants Transformers](<https://devfeed.tech/articles/symmetry-fingerprinting-with-geometric-learnable-invariants-transformers-138998.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20150>)

Author: Bart M. N. Smets, Gijs Bellaard, Pieter Wils

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Transformer](<https://devfeed.tech/topics/transformer.md>), [model architecture](<https://devfeed.tech/topics/model-architecture.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [image-classification](<https://devfeed.tech/tags/image-classification.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [symmetry](<https://devfeed.tech/tags/symmetry.md>), [training-data](<https://devfeed.tech/tags/training-data.md>)

### AI overview

The proposed soft-equivariant neural network is designed to avoid fixing a potentially unsuitable symmetry bias in advance: it selects from chosen symmetry groups during training, becoming equivariant to those that fit the training data. After training, inspecting the network yields a symmetry fingerprint indicating which symmetries mattered and to what degree. The authors demonstrate the architecture and fingerprinting process on image classification. The supplied text does not report comparative performance results or further implementation details.

### Source excerpt

arXiv:2611.20150v1 Announce Type: new Abstract: Geometric deep learning has made available a large variety of structurally equivariant neural network architectures, meaning a particular transformation of their input causes a predictable transformation of their output. But structural equivariance is a very strong inductive bias that can limit performance if chosen poorly. In contrast, choosing an architecture with low geometric bias necessitates data augmentation to obtain correct behavior; extending the training process. We propose a novel neural network architecture that is soft equivariant; we select a set of symmetry groups and during training the network will become equivariant only to those symmetry groups that are appropriate given the training data. After training we can inspect the network to obtain a symmetry fingerprint that will tell us exactly which symmetries ended up being relevant and to what degree. We show how our architecture and the fingerprinting process work in the case of an image classification task.

## Generative Data Augmentation Without External Data: An Empirical and Theoretical Study on Deep Networks

DevFeed: [Generative Data Augmentation Without External Data: An Empirical and Theoretical Study on Deep Networks](<https://devfeed.tech/articles/generative-data-augmentation-without-external-data-an-empirical-and-theoretical-study-on-deep-networks-139174.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21467>)

Author: Daniel Kua, Yan Song

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [generative](<https://devfeed.tech/tags/generative.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [study](<https://devfeed.tech/tags/study.md>), [theoretical](<https://devfeed.tech/tags/theoretical.md>)

### AI overview

The study examines generative data augmentation when generators train only on a classifier's own training set, separating synthetic-data effects from external pretraining. Across four classifier backbones, six datasets (including two medical datasets), and four generators, its excess-risk bound weighs the larger training set against the total variation gap between real and generated data. The bound caps the possible population-risk reduction at the excess risk of the real-only classifier. Experiments suggest synthetic samples help most when classifiers detect a small real/generated discrepancy and the real-only model has room to improve; large detected discrepancies are associated with little benefit or harm. Estimated lower bounds on total variation track weaker gains on five of six datasets, and on CIFAR the most accurate backbone gains least. The bound indicates these trends but does not predict the largest gains' size; most of those gains are also reached by traditional augmentation at the same optimizer-step count.

### Source excerpt

arXiv:2611.21467v1 Announce Type: cross Abstract: Generative data augmentation adds samples from generative models to a classifier's training set. Many influential studies use generators pre-trained on large external datasets, and so mix the value of synthetic data with knowledge transferred through pretraining. We study the case without external data, where each generator learns only from the classifier's own training set, and ask when and why adding generated samples to that training set raises or lowers the classifier's test accuracy. We train classifiers with four backbones on six datasets, two of them medical, adding samples from four generators. We bound the excess risk of a classifier trained with synthetic data, that is, how far its population risk can lie above the minimum risk within its hypothesis class. The bound charges synthetic data for the total variation distance between the real and generated distributions and credits synthetic data for a larger training set. The gain from adding synthetic data, the fall in population risk, is at most the excess risk of the real-only classifier, which trains on the real images alone. Read through the bound, the experiments suggest that synthetic data help most when our classifiers detect only a small discrepancy between the generated and real data and the real-only classifier has room to improve, and that synthetic data help little or hurt when the detected discrepancy is large. Generators with a larger lower bound on the total variation distance, a bound that we estimate from our own classifiers, tend to help less on five of the six datasets, and on the CIFAR datasets the most accurate backbone gains the least. The bound gives these directions but not the size of the largest gains, most of which traditional augmentation also reaches at the same number of optimizer steps.

## Shortcut Learning in Feature-Based Algorithm Selection

DevFeed: [Shortcut Learning in Feature-Based Algorithm Selection](<https://devfeed.tech/articles/shortcut-learning-in-feature-based-algorithm-selection-139052.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20440>)

Author: Shuhei Tanaka, Shoichiro Tanaka, Toshiharu Hatanaka

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Feature Engineering](<https://devfeed.tech/topics/feature-engineering.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [about](<https://devfeed.tech/tags/about.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [after](<https://devfeed.tech/tags/after.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [all](<https://devfeed.tech/tags/all.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [capture](<https://devfeed.tech/tags/capture.md>), [comparison](<https://devfeed.tech/tags/comparison.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ne](<https://devfeed.tech/tags/cs-ne.md>), [data](<https://devfeed.tech/tags/data.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [feature](<https://devfeed.tech/tags/feature.md>), [learning](<https://devfeed.tech/tags/learning.md>), [selection](<https://devfeed.tech/tags/selection.md>)

### AI overview

The Rubber Ruler Test checks whether algorithm-selection models rely on objective-value details that the algorithms themselves ignore: randomly transform test objectives with strictly increasing functions, rerun the algorithms, and measure prediction performance. Comparison-based algorithms such as CMA-ES behave identically under these transformations, so a prediction drop indicates shortcut learning. In 10-dimensional BBOB experiments, a model for two such algorithms fell from R² 0.85 to 0.23 using all ELA features; invariant features alone still scored below 0.45, while rank-based features reduced the drop when algorithms searched by ranks. Training with transformed instances improved prediction on transformed data across the studied portfolios, but reduced original-instance R² by as much as 0.31. The authors recommend reporting this test alongside in-distribution accuracy and using it to guide feature extraction and augmentation.

### Source excerpt

arXiv:2611.20440v1 Announce Type: cross Abstract: Landscape features give learning models information about the objective function for algorithm selection, algorithm configuration, and performance prediction. Should these features capture more information? Not always, because a model may rely on information that the algorithms ignore. This phenomenon is called shortcut learning, and in-distribution accuracy can hide it. We propose the Rubber Ruler Test. It transforms the objective values of test instances with random strictly increasing transformations, reruns the algorithms, and measures prediction performance. Comparison-based algorithms such as CMA-ES perform identically after the transformation, so for them any drop reveals shortcut learning. On 10-dimensional BBOB, a model for two comparison-based algorithms learned shortcuts even from normalized objective values. The R^2 of a model using all ELA features dropped from 0.85 to 0.23, below 0.45 with invariant features only. Rank-based features reduced the drop when algorithms search using ranks. Data augmentation with transformed training instances improved prediction on transformed instances for every portfolio we studied, but lowered R^2 on original instances by up to 0.31. These results suggest that models should rely only on information that the algorithms use. We recommend reporting the Rubber Ruler Test alongside in-distribution accuracy and using it to choose feature extraction and data augmentation.

## Motor Imagery Classification Using Hybrid Cross-Subject Class Mixup and Selective Attention

DevFeed: [Motor Imagery Classification Using Hybrid Cross-Subject Class Mixup and Selective Attention](<https://devfeed.tech/articles/motor-imagery-classification-using-hybrid-cross-subject-class-mixup-and-selective-attention-139102.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20853>)

Author: Jiwon Kim, Chae-Won Lee, Jong-Seok Lee

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [text-classification](<https://devfeed.tech/topics/text-classification.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [attention](<https://devfeed.tech/tags/attention.md>), [bci](<https://devfeed.tech/tags/bci.md>), [brain-computer-interface](<https://devfeed.tech/tags/brain-computer-interface.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [eeg](<https://devfeed.tech/tags/eeg.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [functional](<https://devfeed.tech/tags/functional.md>), [fuse](<https://devfeed.tech/tags/fuse.md>), [hybrid](<https://devfeed.tech/tags/hybrid.md>), [imagery](<https://devfeed.tech/tags/imagery.md>), [infrared](<https://devfeed.tech/tags/infrared.md>), [modal](<https://devfeed.tech/tags/modal.md>), [model](<https://devfeed.tech/tags/model.md>), [motor](<https://devfeed.tech/tags/motor.md>), [spectroscopy](<https://devfeed.tech/tags/spectroscopy.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [token](<https://devfeed.tech/tags/token.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

The framework combines cross-subject class mixup and selective attention to improve hybrid EEG-fNIRS motor imagery classification across subjects. Cross-Subject Class Mixup independently selects EEG and fNIRS donor trials from other training subjects within the anchor class, mixing each modality while preserving its label. Selective Attention applies causal temporal self-attention to EEG and uses a classification token to integrate both modalities, without fNIRS attention updates or direct cross-modal temporal-token attention. In leave-one-subject-out evaluation on a public dataset with 28 subjects, the model reports 76.85% mean balanced accuracy and 76.58% macro-F1, the highest mean performance among five reimplemented baselines. The excerpt also says the authors investigate component contributions through mixing, donor-policy, temporal-policy, cross-modal-path, and ablation comparisons.

### Source excerpt

arXiv:2611.20853v1 Announce Type: new Abstract: Motor imagery (MI) enables a brain-computer interface (BCI) to decode movement intentions without overt movement. Hybrid electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) classification combines complementary signals, but inter-subject variability and the design of information exchange between modalities affect generalization to new subjects. We propose a framework that combines Cross-Subject Class Mixup (CSCM) with Selective Attention. CSCM aims to construct new training data to make the model robust against inter-subject variability. It independently selects EEG and fNIRS donor trials from other training subjects within the anchor class and mixes each modality while preserving the original label. Selective Attention provides an effective way to simultaneously model the temporal signal characteristics and fuse the two modalities. It retains causal temporal self-attention for EEG and uses a classification token (CLS) to integrate both modalities, without fNIRS attention updates or direct cross-modal temporal-token attention. Leave-one-subject-out (LOSO) evaluation across 28 subjects on a public EEG-fNIRS dataset yields a mean balanced accuracy (BA) of 76.85% and a macro-averaged F1 score (Macro-F1) of 76.58%. The proposed model achieves the highest mean performance among five reimplemented baselines. We also examine the contributions of CSCM and Selective Attention through modality-specific mixing and donor-policy comparisons, temporal-policy comparisons, interventions on direct cross-modal paths, and component ablations.

## iGRAIL: Blockchain-Based Generative Federated Learning for Trustworthy Healthcare Intelligence

DevFeed: [iGRAIL: Blockchain-Based Generative Federated Learning for Trustworthy Healthcare Intelligence](<https://devfeed.tech/articles/igrail-blockchain-based-generative-federated-learning-for-trustworthy-healthcare-intelligence-136034.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17703>)

Author: Debashis Das, Sourav Banerjee, Saraju P. Mohanty

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Blockchain](<https://devfeed.tech/topics/blockchain.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Cryptography](<https://devfeed.tech/topics/cryptography.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [smart contract](<https://devfeed.tech/topics/smart-contract.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [blockchain](<https://devfeed.tech/tags/blockchain.md>), [cryptographic](<https://devfeed.tech/tags/cryptographic.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [differential-privacy](<https://devfeed.tech/tags/differential-privacy.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [integrity](<https://devfeed.tech/tags/integrity.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [malicious-update](<https://devfeed.tech/tags/malicious-update.md>), [model](<https://devfeed.tech/tags/model.md>), [patient-data](<https://devfeed.tech/tags/patient-data.md>), [patient-records](<https://devfeed.tech/tags/patient-records.md>), [performance](<https://devfeed.tech/tags/performance.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [privacy-security](<https://devfeed.tech/tags/privacy-security.md>)

### AI overview

iGRAIL combines local generative data augmentation and differential privacy with cryptographic communication, blockchain verification, and smart-contract access control to protect federated healthcare model updates. Across four healthcare datasets, it was compared with conventional federated learning and blockchain-based FL. On two large diabetes datasets, it reportedly improved accuracy by about 5.4-5.6%, F1 by 14.6-16.9%, and MCC by 16.0-18.1% over the best baseline. Stronger differential privacy reduced the privacy-loss parameter ε by about 72.5% on cancer and 87.5% on diabetes, with limited predictive-performance loss. The abstract reports added computational overhead; it does not provide implementation details or enough results to assess the full scalability claims.

### Source excerpt

arXiv:2611.17703v1 Announce Type: new Abstract: Healthcare organizations collect huge amounts of patient data from clinical records, medical tests, monitoring systems, and healthcare services. Such data can underpin intelligent healthcare analytics but remains distributed across institutions and cannot be shared directly due to privacy, security, and trust concerns. Federated learning (FL) enables collaborative learning without sharing raw patient records, but the exchanged model information remains vulnerable to privacy leakage, tampering, replay, and unauthorized access. In this paper, we propose iGRAIL, a blockchain-enabled generative FL framework for trustworthy healthcare intelligence. iGRAIL combines local generative learning for data augmentation with differential privacy to protect sensitive information during local training. Model communication is secured using cryptographic mechanisms, and blockchain-based verification and smart-contract access control ensure that only authorized, authentic, fresh, and integrity-preserving updates are accepted for federated aggregation. The framework is evaluated on four healthcare datasets and compared with the conventional FL and blockchain-based FL (BC-FL) under predictive, privacy, non-IID, scalability, malicious-update, security-verification, and runtime settings. For the two large diabetes datasets, iGRAIL improves accuracy by about 5.4-5.6%, the F1-score by 14.6-16.9%, and MCC by 16.0-18.1% over the best FL or BC-FL baseline. Increasing the strength of differential privacy reduces the privacy-loss parameter $\epsilon$ by about 72.5% for the cancer dataset and 87.5% for the diabetes dataset, with only a limited loss in prediction performance. These results indicate that iGRAIL supports secure and scalable federated computing while preserving privacy, model integrity, and controlled participation, at the cost of additional computational overhead.

## MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals

DevFeed: [MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals](<https://devfeed.tech/articles/mastars-multi-agent-sequential-trajectory-augmentation-with-return-conditioned-subgoals-135116.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17793>)

Author: Jiwon Jeon, Myungsik Cho, Woojun Kim, Seongmin Kim, Woohyeon Byeon, Seungyul Han, Youngchul Sung

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diversity](<https://devfeed.tech/tags/diversity.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [offline](<https://devfeed.tech/tags/offline.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>)

### AI overview

MASTARS addresses the diversity-coordination trade-off in offline multi-agent trajectory augmentation with a diffusion framework that generates trajectories sequentially across agents and uses inpainting to enforce cross-agent consistency. The abstract reports gains across multiple offline MARL methods on MPE, SMAC, and SMAC-v2; it provides no quantitative results or details about the experiments.

### Source excerpt

arXiv:2611.17793v1 Announce Type: new Abstract: The performance of offline Multi-Agent Reinforcement Learning (MARL) is limited by the quality of the fixed offline dataset, motivating trajectory augmentation. However, augmenting multi-agent trajectories presents a fundamental challenge of the diversity-coordination trade-off: independent generation improves diversity but lacks coordination, while joint generation induces coordination but lacks diversity, reproducing the training distribution. To address this challenge in multi-agent data augmentation, we introduce MASTARS, a novel diffusion-based framework that generates multi-agent trajectories sequentially across agents while enforcing cross-agent consistent coordination via the method of inpainting. MASTARS produces trajectories that are diverse, coordinated and globally coherent. Experiments on various benchmarks such as MPE, SMAC, and SMAC-v2 demonstrate significant performance gains across multiple offline MARL methods.

## mlr3torch: A Deep Learning Framework in R based on mlr3 and torch

DevFeed: [mlr3torch: A Deep Learning Framework in R based on mlr3 and torch](<https://devfeed.tech/articles/mlr3torch-a-deep-learning-framework-in-r-based-on-mlr3-and-torch-135680.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2604.18152>)

Author: Sebastian Fischer, Lukas Burk, Carson Zhang, Bernd Bischl, Martin Binder

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Deep learning](<https://devfeed.tech/topics/deep-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Hyperparameter optimization](<https://devfeed.tech/topics/hyperparameter-optimization.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [neural-networks](<https://devfeed.tech/tags/neural-networks.md>), [r](<https://devfeed.tech/tags/r.md>), [regression](<https://devfeed.tech/tags/regression.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [tabular-data](<https://devfeed.tech/tags/tabular-data.md>), [tensors](<https://devfeed.tech/tags/tensors.md>), [torch](<https://devfeed.tech/tags/torch.md>), [use-cases](<https://devfeed.tech/tags/use-cases.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

mlr3torch brings deep learning into R's mlr3 ecosystem, using torch to define, train, and evaluate neural networks for classification and regression on tabular data or tensors such as images. It provides predefined architectures, converts torch models into mlr3 learners, and lets users represent preprocessing, data augmentation, and network architecture together as graphs based on mlr3pipelines. Its integration supports resampling and benchmarking. The abstract also reports examples of hyperparameter tuning, fine-tuning, multimodal architectures, and runtime benchmarks, but gives no benchmark results.

### Source excerpt

arXiv:2604.18152v2 Announce Type: replace-cross Abstract: Deep learning (DL) has become a cornerstone of modern machine learning (ML) praxis. We introduce the R package mlr3torch, which is an extensible DL framework for the mlr3 ecosystem. It is built upon the torch package, and simplifies the definition, training, and evaluation of neural networks for both tabular data and generic tensors (e.g., images) for classification and regression. The package implements predefined architectures, and torch models can easily be converted to mlr3 learners. It also allows users to define neural networks as graphs. This representation is based on the graph language defined in mlr3pipelines and allows users to define the entire modeling workflow, including preprocessing, data augmentation, and network architecture, in a single graph. Through its integration into the mlr3 ecosystem, the package allows for convenient resampling, benchmarking, preprocessing, and more. We explain the package's design and features and show how to customize and extend it to new problems. Furthermore, we demonstrate the package's capabilities using three use cases, namely hyperparameter tuning, fine-tuning, and defining architectures for multimodal data. Finally, we present some runtime benchmarks.

## Hard/Soft NLoS Detection via Combinatorial Data Augmentation for 6G Positioning

DevFeed: [Hard/Soft NLoS Detection via Combinatorial Data Augmentation for 6G Positioning](<https://devfeed.tech/articles/hard-soft-nlos-detection-via-combinatorial-data-augmentation-for-6g-positioning-134909.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2603.07932>)

Author: Sang-Hyeok Kim (Inha University, South Korea), Seung Min Yu (Korea Railroad Research Institute, South Korea), Jihong Park (Singapore University of Technology and Design, Singapore), Seung-Woo Ko (Inha

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>)

Tags: [6g](<https://devfeed.tech/tags/6g.md>), [cs-it](<https://devfeed.tech/tags/cs-it.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [data](<https://devfeed.tech/tags/data.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [detection](<https://devfeed.tech/tags/detection.md>), [math-it](<https://devfeed.tech/tags/math-it.md>), [positioning](<https://devfeed.tech/tags/positioning.md>)

### AI overview

CDA-ND detects non-line-of-sight (NLoS) gNodeBs from one snapshot of range measurements by multilaterating across many gNB combinations. If a gNB is NLoS, preliminary location estimates made with and without its measurement form displaced clusters; their displacement yields an NLoS evidence vector and likelihood score. Hard decision labels each gNB using a threshold. Soft decision estimates NLoS confidence using weak site-survey priors, then excludes NLoS gNBs and reweights the rest for positioning. In indoor factory frequency-range-1 settings, reported detection accuracy was 96.8% with about 18% NLoS gNBs and 91.5% with about 56%; positioning mean absolute error fell by about 22% in LoS-dominant and 67% in NLoS-dominant environments.

### Source excerpt

arXiv:2603.07932v2 Announce Type: replace-cross Abstract: A key enabler for meeting the stringent requirements of 6G positioning is the ability to exploit site-dependent information governing line-of-sight (LoS) and non-line-of-sight (NLoS) propagation. However, acquiring such environmental information in real time is challenging in practice. To address this issue, we propose a novel NLoS detection algorithm termed combinatorial data augmentation-guided NLoS detection (CDA-ND), which builds upon our prior work. CDA-ND generates numerous preliminary estimated locations (PELs) by applying multilateration over many gNodeB (gNB) combinations using a single snapshot of range measurements. When a target gNB is in NLoS, the resulting PELs split into two clusters: one derived using the target gNB's range measurement and the other derived without it. Their displacement is summarized by a single vector, called the NLoS evidence vector (NEV), which is used to compute an NLoS likelihood score. Based on this score, two modes of NLoS detection are developed. First, each gNB is classified as LoS or NLoS, termed hard decision (HD), using a simple threshold test. Second, each gNB's NLoS confidence is probabilistically quantified, termed soft decision (SD), which extends HD with weak site-survey priors, namely empirical NLoS-score samples and the average NLoS probability. We then design positioning algorithms tailored to these two modes by excluding gNBs deemed NLoS and re-weighting the remaining gNBs for SD. The proposed CDA-ND achieves high reliability in indoor factory environments under frequency range 1, attaining NLoS detection accuracies of 96.8% and 91.5% when the proportion of NLoS gNBs is approximately 18% and 56%, respectively. As a result, integrating CDA-ND into positioning significantly reduces mean absolute error by about 22% and 67% in LoS- and NLoS-dominant environments, respectively.

## Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training

DevFeed: [Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training](<https://devfeed.tech/articles/learning-where-to-simulate-generative-active-sampling-for-online-pde-surrogate-training-131929.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.09949>)

Author: Pierre Cesar (DATAMOVE), Sofya Dymchenko (DATAMOVE), Abhishek Purandare (DATAMOVE), Bruno Raffin (DATAMOVE)

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [2d](<https://devfeed.tech/tags/2d.md>), [architectures](<https://devfeed.tech/tags/architectures.md>), [conditional](<https://devfeed.tech/tags/conditional.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [dispersion](<https://devfeed.tech/tags/dispersion.md>), [error](<https://devfeed.tech/tags/error.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fast](<https://devfeed.tech/tags/fast.md>), [generate](<https://devfeed.tech/tags/generate.md>), [generative](<https://devfeed.tech/tags/generative.md>), [learning](<https://devfeed.tech/tags/learning.md>), [model](<https://devfeed.tech/tags/model.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [online](<https://devfeed.tech/tags/online.md>), [published](<https://devfeed.tech/tags/published.md>), [sampling](<https://devfeed.tech/tags/sampling.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

OGAS adapts PDE simulation configurations continuously during surrogate training: a parallel diffusion model learns to sample configurations conditioned on difficulty signals such as loss or uncertainty, prioritizing challenging cases as new simulations are generated. This differs from classical round-based active learning. Across 2D Kuramoto-Sivashinsky, Navier-Stokes, and Gray-Scott PDEs, multiple surrogate architectures, and up to 308 configuration parameters, the paper reports lower 99th-percentile prediction error and overall error dispersion than uniform sampling, with negligible wall-clock overhead. These findings are limited to the tested PDEs and architectures.

### Source excerpt

arXiv:2606.09949v2 Announce Type: replace-cross Abstract: Paper published at NeurIPS 2026. For data-driven PDE surrogates, generalizing across a wide range of initial conditions and physical coefficients requires a training set of numerical simulations that consistently covers the resulting dynamics. Yet uniform sampling of these configuration parameters can leave challenging regimes insufficiently covered, leading to high prediction errors and large error variance in the trained surrogate. To address this sampling imbalance, we introduce the Online Generative Active Sampling (OGAS), which continuously adapts configuration sampling during surrogate training, as an alternative to classical round-based active learning. As the surrogate learns from a stream of simulation data generated online, OGAS trains a fast diffusion model in parallel to sample configuration parameters conditioned on a training difficulty signal, such as loss or uncertainty. This conditional sampler enables OGAS to parametrize subsequent simulations to generate challenging training data by prioritizing configurations with high difficulty values. We evaluate OGAS on 2D PDEs with distinct challenging dynamics-Kuramoto--Sivashinsky, Navier--Stokes, and Gray--Scott-using multiple surrogate architectures and up to 308 configuration parameters. Across the tested PDEs and architectures, OGAS consistently reduces the 99th-percentile prediction error and overall error dispersion compared with uniform sampling, while wall-clock overhead is negligible. Code and experiments are available at https://github.com/melissa-sa/ogas.

## Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification

DevFeed: [Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification](<https://devfeed.tech/articles/lightweight-genai-for-network-traffic-generation-fidelity-augmentation-and-classification-131571.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2603.25507>)

Author: Giampaolo Bovenzi, Domenico Ciuonzo, Jonatan Krolikowski, Antonio Montieri, Alfredo Nascita, Antonio Pescap\\\`e, Dario Rossi

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [network-intelligence](<https://devfeed.tech/topics/network-intelligence.md>), [Internet Traffic](<https://devfeed.tech/topics/internet-traffic.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [genai](<https://devfeed.tech/tags/genai.md>), [generation](<https://devfeed.tech/tags/generation.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [network-traffic](<https://devfeed.tech/tags/network-traffic.md>), [state-space-models](<https://devfeed.tech/tags/state-space-models.md>), [synthetic-data](<https://devfeed.tech/tags/synthetic-data.md>), [transformer](<https://devfeed.tech/tags/transformer.md>)

### AI overview

The study evaluates lightweight generative models for network traffic generation using compact flow representations derived from early packet headers, rather than raw packet bytes or large foundation models. Models with a few million parameters are assessed for traffic fidelity, downstream classification trained only on synthetic data, low-data augmentation, and computational efficiency. On two heterogeneous datasets, transformer and state-space models preserve static and temporal traffic characteristics and produce useful data for network traffic classification. Transformer models provide the best reported fidelity-efficiency trade-off, with high-quality generation and moderate computational overhead.

### Source excerpt

arXiv:2603.25507v3 Announce Type: replace Abstract: Network Traffic Classification (NTC) increasingly relies on data-driven models, yet its practical deployment is often constrained by limited labeled data, strict privacy requirements, and the cost of collecting representative traffic traces. While Network Traffic Generation (NTG) provides an effective means to mitigate data scarcity, conventional generative methods struggle to model the complex temporal dynamics of modern traffic and often incur high computational costs. In this article, we investigate lightweight Generative Artificial Intelligence (GenAI) architectures for practical NTG. Rather than generating raw packet bytes or relying on large foundation models, we synthesize compact flow-level traffic representations derived from early packet-header information, enabling transformer-based, state-space, and diffusion models with only a few million parameters. We present a modular GenAI pipeline for NTG and evaluate it along four complementary axes: (i) synthetic traffic fidelity, (ii) synthetic-only training for reduced raw-data sharing in NTC, (iii) data augmentation under low-data regimes, and (iv) computational efficiency. Experiments on two heterogeneous datasets show that lightweight transformer-based and state-space models preserve both static and temporal traffic characteristics, while providing useful synthetic data for downstream NTC. Among them, transformer-based models offer the best fidelity-efficiency trade-off, combining high-quality traffic generation with moderate computational overhead.

## Fine-Tuned Small Language Model for Synthetic Clinical Data Generation and Predictive Healthcare Analytics

DevFeed: [Fine-Tuned Small Language Model for Synthetic Clinical Data Generation and Predictive Healthcare Analytics](<https://devfeed.tech/articles/fine-tuned-small-language-model-for-synthetic-clinical-data-generation-and-predictive-healthcare-analytics-132238.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16460>)

Author: Mihnea Sebastian Burlacu, Ionut Anghel, Tudor Cioara

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [few-shot](<https://devfeed.tech/topics/few-shot.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [analytics](<https://devfeed.tech/tags/analytics.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classification-accuracy](<https://devfeed.tech/tags/classification-accuracy.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [deep-learning](<https://devfeed.tech/tags/deep-learning.md>), [few-shot](<https://devfeed.tech/tags/few-shot.md>), [fine](<https://devfeed.tech/tags/fine.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [generation](<https://devfeed.tech/tags/generation.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [lstm](<https://devfeed.tech/tags/lstm.md>), [model](<https://devfeed.tech/tags/model.md>), [predictive-healthcare](<https://devfeed.tech/tags/predictive-healthcare.md>), [small](<https://devfeed.tech/tags/small.md>), [small-language-model](<https://devfeed.tech/tags/small-language-model.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>)

### AI overview

The study reports that synthetic clinical data generated with a medically fine-tuned Microsoft Phi-2 improved a vital-sign classifier's accuracy from 89.0% to 93.7%. The researchers fine-tuned Phi-2 on MedQuad using QLoRA and few-shot prompting, then used it to augment a small dataset of vital-sign values labeled as pathological or physiological. The fine-tuned model scored higher than pretrained Phi-2 on ROUGE and BERTScore, and augmentation also consistently improved the LSTM model's precision, recall, and F1-score. The evidence provided is the abstract; it does not describe the dataset size or further experimental details.

### Source excerpt

arXiv:2611.16460v1 Announce Type: new Abstract: The reduced availability of medical datasets represents an important challenge in the development of predictive models for remote healthcare solutions, especially when the available data are imbalanced or difficult to extend through traditional methods. Small Language Models (SLMs) have become a promising alternative to Large Language Models (LLMs) for addressing these limitations due to their lower computational requirements and adaptability to specialized tasks. However, their performance remains highly dependent on the quality and representativeness of the available training data. In this paper, we propose a method for clinical data augmentation based on a fine-tuned Microsoft Phi-2 model that is used to generate synthetic instances, with the purpose of improving deep learning-based model for predicting remotely monitored vital signs. The Phi-2 model was adapted to the medical domain through supervised fine-tuning on the MedQuad dataset, through a Quantized Low-Rank Adaptation (QLoRA)-based method and by applying few-shot prompting techniques. The resulting model was used afterwards in the augmentation of a small-sized dataset, composed of vital sign values and labels associated with pathological and physiological states. The experimental results demonstrate that fine-tuned SLMs improved the performance on medical domain, achieving higher scores for both lexical (ROUGE) and semantic (BERTScore) evaluation metrics compared to the pretrained model. Moreover, the fine-tuned SLM is effective for generating structured synthetic clinical data. When used for data augmentation, the generated dataset improved the performance of a LSTM predictive model, increasing the classification accuracy from 89.0% to 93.7% and showing consistent improvements in precision, recall, and F1-score.

## MutAtlas: A PDB-Wide Energy-Guided Atlas of Protein Mutation Effects

DevFeed: [MutAtlas: A PDB-Wide Energy-Guided Atlas of Protein Mutation Effects](<https://devfeed.tech/articles/mutatlas-a-pdb-wide-energy-guided-atlas-of-protein-mutation-effects-133114.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16361>)

Author: Ruihan Guo, Chaoran Cheng, Zhanghan Ni, Neil He, Bangji Yang, Ge Liu

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [atlas](<https://devfeed.tech/tags/atlas.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [effects](<https://devfeed.tech/tags/effects.md>), [energy](<https://devfeed.tech/tags/energy.md>), [mutation](<https://devfeed.tech/tags/mutation.md>), [pdb](<https://devfeed.tech/tags/pdb.md>), [q-bio-gn](<https://devfeed.tech/tags/q-bio-gn.md>)

### AI overview

MutAtlas augments sparse experimental mutation data by exhaustively enumerating single-site substitutions on experimentally resolved PDB structures and aligning signals from physics-based energy, protein language, and inverse folding models. The models show pervasive differences in mutation preferences, which the authors attribute to conflicting inductive biases. Their unsupervised distillation framework learns relative preferences while modeling disagreement, uses no experimental mutation labels during training, and outperforms the evaluated zero-shot baselines and naive multi-source fusion strategies on ProteinGym. The authors release the dataset and evaluation pipeline.

### Source excerpt

arXiv:2611.16361v1 Announce Type: new Abstract: Protein mutation effect prediction is fundamental to protein engineering and disease variant interpretation, yet experimentally measured mutation data remain accurate but extremely sparse. To provide scalable supplementary mutation signals, we construct a PDB-wide mutation augmentation dataset that exhaustively enumerates single-site substitutions on experimentally resolved protein structures and aligns mutation signals from physics-based energy models, protein language models, and inverse folding models. Large-scale analysis under a unified mutation preference representation reveals substantial differences in the consistency, concentration, and substitution patterns of mutation distributions across models, indicating that disagreement is pervasive and reflects conflicting inductive biases rather than random noise. Motivated by these observations, we propose an unsupervised multi-source mutation preference distillation framework that learns from relative mutation preferences while explicitly modeling cross-source disagreement. Without using any experimental mutation labels during training, our approach achieves the best overall performance among the evaluated zero-shot baselines and naive multi-source fusion strategies on ProteinGym. We release the dataset and evaluation pipeline to support reproducible studies of protein mutation effects.

## Edge-Gradient Augmentation under Reinforcement Learning for Temporal Graph

DevFeed: [Edge-Gradient Augmentation under Reinforcement Learning for Temporal Graph](<https://devfeed.tech/articles/edge-gradient-augmentation-under-reinforcement-learning-for-temporal-graph-132270.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.16678>)

Author: Yongqing Zhou, Jiawei Chen, Wenjun Wang, Xinyu Wang, Wei Yu, Qiyao Peng

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [mlp](<https://devfeed.tech/topics/mlp.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [area](<https://devfeed.tech/tags/area.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [can](<https://devfeed.tech/tags/can.md>), [change](<https://devfeed.tech/tags/change.md>), [channel](<https://devfeed.tech/tags/channel.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [edge](<https://devfeed.tech/tags/edge.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [graph](<https://devfeed.tech/tags/graph.md>), [learning](<https://devfeed.tech/tags/learning.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [under](<https://devfeed.tech/tags/under.md>)

### AI overview

EG-RL targets temporal link prediction by explicitly encoding edge births and deaths, then using reinforcement learning to select and augment informative edge snapshots. Its policy receives critic-based feedback to optimize prediction accuracy. The architecture combines node and link encoding, token and channel mixing, global pooling, and a two-layer MLP classifier. The abstract reports gains in AUC and average precision across multiple dynamic graph datasets; ablations support the adaptive augmentation and encoding mechanisms. The excerpt gives no dataset names, numerical results, or comparison details.

### Source excerpt

arXiv:2611.16678v1 Announce Type: cross Abstract: Temporal link prediction is critical for understand- ing dynamic interactions in evolving networks, informing appli- cations ranging from social network analysis to recommendation systems. Existing methods typically rely on raw temporal graph data, often neglecting explicit edge-change information that can significantly improve predictive performance. To address this gap, we propose edge-gradient reinforced learning (EG-RL), a framework that explicitly encodes edge-gradient events (edge births and deaths) through dedicated node and link encoding modules. EG-RL uses a policy-driven reinforcement-learning mechanism to dynamically select and augment the most infor- mative edge snapshots, guided by critic-based feedback to opti- mize prediction accuracy. The model comprises distinct modules for node encoding, link encoding, token mixing, and channel mixing, integrated through global pooling and followed by a two-layer multilayer perceptron classifier. Extensive experiments on multiple dynamic graph datasets demonstrate substantial gains in area under the receiver operating characteristic curve and average precision. Ablation studies further confirm the necessity of adaptive edge-gradient augmentation and validate the effectiveness of the proposed encoding and reinforcement- learning mechanisms.

## Synthetic Data Augmentation for Fairness under Data Imbalance: Theory and Adaptive Allocation

DevFeed: [Synthetic Data Augmentation for Fairness under Data Imbalance: Theory and Adaptive Allocation](<https://devfeed.tech/articles/synthetic-data-augmentation-for-fairness-under-data-imbalance-theory-and-adaptive-allocation-132925.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14870>)

Author: Zhengchi Ma, Kaifeng Zhang, Anru R. Zhang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [responsible-ai](<https://devfeed.tech/topics/responsible-ai.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [application](<https://devfeed.tech/tags/application.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [fairness](<https://devfeed.tech/tags/fairness.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [stat-me](<https://devfeed.tech/tags/stat-me.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [theory](<https://devfeed.tech/tags/theory.md>)

### AI overview

The paper examines how prevalence imbalance and group-size imbalance can shift a classifier's decision boundary and create disparities in group true positive rates under Equal Opportunity. It studies exact synthetic augmentation to equalize every group-label cell, establishing conditions for improved Equal Opportunity and convergence toward the oracle balanced classifier as sample size grows and generator error vanishes. Because full balancing may not give the best fairness-accuracy trade-off, it proposes ACASA, which chooses where and how much to augment to minimize estimated disparity subject to an accuracy constraint. The abstract reports finite-sample guarantees for both approaches and says simulations and a real-data application show substantial disparity reductions with favorable empirical trade-offs.

### Source excerpt

arXiv:2611.14870v1 Announce Type: cross Abstract: Data imbalance across sensitive groups and class labels is common in classification problems and can contribute to substantial fairness disparities. We study how such imbalance affects Equal Opportunity and how synthetic data augmentation can mitigate the resulting unfairness. We first identify two mechanisms, prevalence imbalance and group-size imbalance, through which changes in the training distribution shift the learned decision boundary and induce disparities in group true positive rates. Motivated by this analysis, we study exact full-balance augmentation, which equalizes all group-label cells. We establish conditions under which full balancing strictly improves Equal Opportunity together with a prediction-error comparison under the oracle balanced distribution, and show that the Equal Opportunity gap of the synthetic-data classifier converges to that of the oracle balanced classifier as the sample size grows and the generator error vanishes. The finite-sample convergence rate agrees, up to logarithmic factors and generator-approximation error, with the information-theoretic lower-bound rate under the corresponding regularity regimes. Since exact balancing need not provide the best fairness-accuracy trade-off in practice, we further propose Accuracy-Constrained Adaptive Synthetic Augmentation (ACASA), which learns both where and how much to augment by minimizing estimated fairness disparity subject to a constraint on predictive accuracy. We provide a finite-sample guarantee comparing the selected augmentation allocation with the population-optimal accuracy-feasible allocation. Simulation studies and real data application support the theoretical findings and demonstrate that synthetic augmentation can substantially reduce fairness disparities while achieving favorable empirical fairness-accuracy trade-offs.

## GenPFN: An In-Context Tabular Foundation Model Approach for Augmenting Small Datasets in Engineering

DevFeed: [GenPFN: An In-Context Tabular Foundation Model Approach for Augmenting Small Datasets in Engineering](<https://devfeed.tech/articles/genpfn-an-in-context-tabular-foundation-model-approach-for-augmenting-small-datasets-in-engineering-132052.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14804>)

Author: Noah J. Bagazinski, Cyril Picard, Faez Ahmed

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [few-shot-learning](<https://devfeed.tech/topics/few-shot-learning.md>)

Tags: [1-4](<https://devfeed.tech/tags/1-4.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [adversarial](<https://devfeed.tech/tags/adversarial.md>), [approach](<https://devfeed.tech/tags/approach.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [autoencoder](<https://devfeed.tech/tags/autoencoder.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [candidate](<https://devfeed.tech/tags/candidate.md>), [case](<https://devfeed.tech/tags/case.md>), [case-study](<https://devfeed.tech/tags/case-study.md>), [class](<https://devfeed.tech/tags/class.md>), [comparisons](<https://devfeed.tech/tags/comparisons.md>), [context](<https://devfeed.tech/tags/context.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [model](<https://devfeed.tech/tags/model.md>), [small](<https://devfeed.tech/tags/small.md>)

### AI overview

GenPFN generates and evaluates engineering design candidates to augment small datasets for regression training. It uses a fixed-weight pretrained TabPFN classifier to guide interpolation between desired designs, with gated classifier gradients and Gaussian noise; candidates are then checked against problem constraints and objectives, and evaluated desired designs are added to the training context. Across fourteen selected problems, paired comparisons report higher class satisfaction and lower realism distance than the tested adversarial, VAE, and diffusion generators, while the VAE has greater coverage and diversity. Compared with SMOTE, GenPFN has lower coverage distance and greater diversity. In observed paired fits, augmentation reduced estimated AutoGluon validation MSE by 62.1% versus context-only training. In a hull-stern case study, 99.3% of generated candidates were propeller-compatible, compared with 1.4% of randomly sampled context designs.

### Source excerpt

arXiv:2611.14804v1 Announce Type: new Abstract: Costly simulations and experiments limit the data available for engineering design. This paper proposes GenPFN, a training-free candidate generator guided by a pretrained tabular Prior-Data Fitted Network (TabPFN) classifier with fixed weights. The context contains evaluated designs labeled desired (Class 1) or undesired (Class 0). GenPFN interpolates between desired designs and refines candidates using gated classifier gradients and Gaussian noise. Each candidate is evaluated using the problem's constraints and objective functions. Evaluated desired designs and their objective values augment the context for regression training. Evaluation spans fourteen selected problems, including a two-parameter benchmark and a 44-parameter hull problem. In paired comparisons, GenPFN with TabPFN v1 achieves higher class satisfaction and lower realism distance than the tested adversarial, variational-autoencoder and diffusion generators. The variational-autoencoder generator provides greater coverage and diversity. Relative to the synthetic minority over-sampling technique (SMOTE), GenPFN provides lower coverage distance and greater diversity. Among observed paired regression fits, augmentation reduces estimated AutoGluon validation mean squared error by 62.1% relative to context-only training. A hull-stern case study yields 99.3% propeller-compatible candidates versus 1.4% among randomly sampled context designs. Generation followed by evaluation produces sample sets that augment limited datasets and support training more accurate predictive models.

## Data augmentation using generative networks to identify dementia

DevFeed: [Data augmentation using generative networks to identify dementia](<https://devfeed.tech/articles/data-augmentation-using-generative-networks-to-identify-dementia-128059.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2004.05989>)

Author: Bahman Mirheidari, Yilin Pan, Daniel Blackburn, Ronan O'Malley, Traci Walker, Annalena Venneri, Markus Reuber, Heidi Christensen

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [audio](<https://devfeed.tech/tags/audio.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sd](<https://devfeed.tech/tags/cs-sd.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [detection](<https://devfeed.tech/tags/detection.md>), [eess-as](<https://devfeed.tech/tags/eess-as.md>), [generative-models](<https://devfeed.tech/tags/generative-models.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [score](<https://devfeed.tech/tags/score.md>), [speech](<https://devfeed.tech/tags/speech.md>)

### AI overview

The study tests generative data augmentation on speech and audio features from interactions recorded by an automatic dementia detection system, addressing limited medical training data. Synthesized samples from two generative models were used to improve a DNN classifier. The abstract reports that a variational autoencoder raised the F-score of a four-way classifier for typical memory-clinic patient groups from 58% to around 74%. It does not specify the second model's result or provide further methodological details in the supplied excerpt.

### Source excerpt

arXiv:2004.05989v1 Announce Type: cross Abstract: Data limitation is one of the most common issues in training machine learning classifiers for medical applications. Due to ethical concerns and data privacy, the number of people that can be recruited to such experiments is generally smaller than the number of participants contributing to non-healthcare datasets. Recent research showed that generative models can be used as an effective approach for data augmentation, which can ultimately help to train more robust classifiers sparse data domains. A number of studies proved that this data augmentation technique works for image and audio data sets. In this paper, we investigate the application of a similar approach to different types of speech and audio-based features extracted from interactions recorded with our automatic dementia detection system. Using two generative models we show how the generated synthesized samples can improve the performance of a DNN based classifier. The variational autoencoder increased the F-score of a four-way classifier distinguishing the typical patient groups seen in memory clinics from 58% to around 74%, a 16% improvement

## FaST: Factored Synthesis of Transitions for Offline Reinforcement Learning

DevFeed: [FaST: Factored Synthesis of Transitions for Offline Reinforcement Learning](<https://devfeed.tech/articles/fast-factored-synthesis-of-transitions-for-offline-reinforcement-learning-128647.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13013>)

Author: Daniel Campa, Spandan Das, Srinjoy Das

Published: 2026-11-11T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [offline-reinforcement-learning](<https://devfeed.tech/tags/offline-reinforcement-learning.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [synthesis](<https://devfeed.tech/tags/synthesis.md>)

### AI overview

FaST factors offline reinforcement learning transitions into state, action, dynamics, reward, and terminal stages, using an estimator suited to each. Across 12 D4RL locomotion and maze benchmarks, TD3+BC and IQL trained on FaST data matched the SynthER diffusion baseline while generating transitions over 90 times faster. FaST can also redraw actions for a fixed state, selecting the highest-advantage candidate under a value function fit to the same data. With 10 candidates, this improved results over real-data training in 11 of 12 medium and medium-replay settings, averaging +8.9 D4RL points and reaching +28.4; it was competitive with advantage-filtered SynthER at lower generation cost. On expert mixtures, both targeting approaches degraded similarly, which the authors attribute to the advantage estimate.

### Source excerpt

arXiv:2611.13013v1 Announce Type: new Abstract: Synthetic data augmentation promises to scale offline reinforcement learning beyond fixed logged datasets, but leading diffusion-based generators model the transition tuple (state, action, next state, reward, terminal) as a monolith: no single factor can be natively redrawn in isolation. We present FaST (Factored Synthesis of Transitions), which factors transitions via the chain rule into state, action, dynamics, reward, and terminal stages, fitting each with an estimator matched to its statistical properties. Across twelve D4RL locomotion and maze benchmarks, TD3+BC and IQL agents trained on FaST transitions match the SynthER diffusion baseline while generating transitions over 90x faster. The explicit action-given-state conditional can also be re-queried for a fixed state, enabling targeted action synthesis: drawing N candidate actions per generated state and keeping the highest-advantage one under a value function fit to the same data, thereby synthesizing improved behavior during generation rather than filtering for it post-hoc. Best-of-10 synthesis beats training on real data on 11 of 12 medium and medium-replay settings (+8.9 D4RL points on average, up to +28.4), and is competitive with advantage-filtered SynthER at a fraction of its generation cost. On expert mixtures both mechanisms degrade identically, tracing the failure to the advantage estimate itself rather than to either targeting mechanism.

## Don't Blame The Preferences: Examining The Emergence of Sycophancy in LLM Training

DevFeed: [Don't Blame The Preferences: Examining The Emergence of Sycophancy in LLM Training](<https://devfeed.tech/articles/don-t-blame-the-preferences-examining-the-emergence-of-sycophancy-in-llm-training-125873.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10045>)

Author: Chao Peter Yang, Catherine Zehr, Pranav Bijith, Brandon Fain

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [post-training](<https://devfeed.tech/topics/post-training.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [dpo](<https://devfeed.tech/topics/dpo.md>), [rlhf](<https://devfeed.tech/topics/rlhf.md>), [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-sycophancy](<https://devfeed.tech/tags/ai-sycophancy.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [dpo](<https://devfeed.tech/tags/dpo.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [interpretability](<https://devfeed.tech/tags/interpretability.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-training](<https://devfeed.tech/tags/llm-training.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mechanistic-interpretability](<https://devfeed.tech/tags/mechanistic-interpretability.md>), [model](<https://devfeed.tech/tags/model.md>), [training](<https://devfeed.tech/tags/training.md>)

### AI overview

Across three model families and three benchmarks, the study finds sycophancy is largely present by the end of supervised fine-tuning (SFT), rather than being mainly introduced by preference alignment. SFT checkpoints score at least 92% as high as preference-aligned models and at least 85% as high as final models; on average they are about as sycophantic as the final models. Preference alignment raises sycophancy in four of nine model-benchmark cases, by an average of 4.2 percentage points in those cases. Mechanistic interpretability analysis finds SFT datasets have roughly the same average activation of sycophancy-related representations as other training data, but contribute substantially more examples; the highest-scoring individual datasets are all from SFT. The authors suggest addressing sycophancy across the training pipeline, particularly through pre-training and SFT data selection and augmentation.

### Source excerpt

arXiv:2611.10045v1 Announce Type: new Abstract: AI sycophancy, the tendency of large language models (LLMs) to flatter users and affirm their beliefs, can undermine accuracy and contribute to misinformation, dependence, and overconfidence. Although prior work has benchmarked sycophancy in released models and proposed mitigations, its origins during training remain poorly understood. Preference alignment methods such as RLHF and DPO are often blamed, but their effects are rarely compared with earlier training stages. We investigate sycophancy across the training pipelines of three model families and three benchmarks. We find that sycophancy is largely established by the end of supervised fine-tuning (SFT), rather than introduced by preference alignment. Across all nine model benchmark combinations, SFT checkpoints attain at least 92% of preference aligned models' sycophancy scores and at least 85% of final models' scores; on average, they are about as sycophantic as final models. Preference alignment increases sycophancy in only four of nine cases, by an average of 4.2 percentage points when it does. To probe the underlying causes, we isolate model representations associated with sycophancy using mechanistic interpretability and measure their activation on training datasets from each stage. SFT datasets show roughly the same average activation as other training data but contribute substantially more examples, and the highest-scoring individual datasets all come from SFT. Our findings suggest that addressing sycophancy requires interventions throughout the training pipeline, particularly in data selection and augmentation for pre-training and SFT.

## VeV: Video-Enhanced Vibration Data Augmentation For Structural Difference

DevFeed: [VeV: Video-Enhanced Vibration Data Augmentation For Structural Difference](<https://devfeed.tech/articles/vev-video-enhanced-vibration-data-augmentation-for-structural-difference-125906.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10257>)

Author: Joonhee Lee, Jiale Zhang, Sungmin Lee, Ruiqing Wang, Jeffrey Shulkin, Yiwen Dong, Pei Zhang, JeongGil Ko

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [data augmentation](<https://devfeed.tech/topics/data-augmentation.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [ambient-intelligence](<https://devfeed.tech/tags/ambient-intelligence.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [data-augmentation](<https://devfeed.tech/tags/data-augmentation.md>), [digital-twins](<https://devfeed.tech/tags/digital-twins.md>), [farm](<https://devfeed.tech/tags/farm.md>), [sensing](<https://devfeed.tech/tags/sensing.md>), [sensor](<https://devfeed.tech/tags/sensor.md>), [sim-to-real](<https://devfeed.tech/tags/sim-to-real.md>), [spatial](<https://devfeed.tech/tags/spatial.md>), [structure](<https://devfeed.tech/tags/structure.md>), [video](<https://devfeed.tech/tags/video.md>)

### AI overview

VeV synthesizes vibration responses at unmeasured structural locations from sparse sensor observations, using monocular video to map possible wave-guiding paths and visual features to represent transient sources and material dynamics. On 1,237 sensor-hours from a sow and piglet farm spanning different structures, it reportedly reduced waveform reconstruction MSE by over 57.5% versus data-driven baselines and reached up to 81.69% zero-shot classification accuracy. The abstract says peak performance required 30-50 calibration chunks; results are reported for this farm evaluation.

### Source excerpt

arXiv:2611.10257v1 Announce Type: cross Abstract: Surface-mounted vibration sensing provides non-invasive structural monitoring with high temporal fidelity across diverse ubiquitous computing scenarios such as smart farms, yet structure-borne wave models remain fragile to physical relocation and structural shifts. However, addressing this spatial data discontinuity remains limited by costly manual recalibration, insufficient physical grounding in data-driven synthesis, and substantial sim-to-real gaps in numerical digital twins. To resolve this spatial bottleneck without labor-intensive data recollection, we propose VeV, a physics-consistent spatial augmentation framework that synthesizes vibration responses at unmeasured target coordinates from sparse reference observations by coupling a monocular Vision-Derived Propagation Possibility Map for structural wave-guiding paths with a Visual Feature Map for transient source kinetics and implicit material dynamics. Evaluated on a 1,237 sensor-hour sow pig and piglet farm across disparate structures, VeV reduces waveform reconstruction MSE by over 57.5% compared to data-driven baselines and achieves up to 81.69% zero-shot classification accuracy, while reaching peak performance within just 30-50 calibration chunks to effectively eliminate cold-start retraining overhead and establish a scalable foundation extending to human-centric floor vibration sensing and ambient intelligence.

[Next page](<https://devfeed.tech/topics/data-augmentation.md?cursor=WyIyMDI2LTExLTEwVDA1OjAwOjAwKzAwOjAwIiwgIjliZjM0YWFlLWI5ZDQtNDEzYi05YWViLTdiYzc4NTUyODVhNyJd>)