# Federated Learning

A decentralized machine learning approach that keeps training data on devices and builds a shared model from locally computed updates.

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

## How Network Topology and Data Heterogeneity Shape Decentralized Learning: A Spectral Analysis

DevFeed: [How Network Topology and Data Heterogeneity Shape Decentralized Learning: A Spectral Analysis](<https://devfeed.tech/articles/how-network-topology-and-data-heterogeneity-shape-decentralized-learning-a-spectral-analysis-145143.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26104>)

Author: Luigi Palmieri, Lorenzo Valerio, Chiara Boldrini, Andrea Passarella, Marco Conti, J\\'anos Kert\\'esz

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [communication](<https://devfeed.tech/tags/communication.md>), [connectivity](<https://devfeed.tech/tags/connectivity.md>), [consensus](<https://devfeed.tech/tags/consensus.md>), [contribution](<https://devfeed.tech/tags/contribution.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-si](<https://devfeed.tech/tags/cs-si.md>), [decentralized](<https://devfeed.tech/tags/decentralized.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [influence](<https://devfeed.tech/tags/influence.md>), [information](<https://devfeed.tech/tags/information.md>), [irregular](<https://devfeed.tech/tags/irregular.md>), [learning](<https://devfeed.tech/tags/learning.md>), [network](<https://devfeed.tech/tags/network.md>), [topology](<https://devfeed.tech/tags/topology.md>)

### AI overview

The paper separates decentralized learning's topology effects into two mechanisms: the dominant eigenmode sets the consensus trajectory and node influence, while non-dominant eigenmodes govern disagreement. Under uniform neighborhood averaging, stationary influence is proportional to node degree plus one; the authors also derive a disagreement bound involving spectral mixing and gradient heterogeneity. Experiments report nearly identical learning dynamics across regular and heterogeneous topologies with IID data. With non-IID data, network size and connectivity affect how unevenly information is learned, and the distribution of data across nodes shapes local contributions to consensus.

### Source excerpt

arXiv:2611.26104v1 Announce Type: new Abstract: Network topology influences decentralized federated learning through information mixing and the relative contribution of individual nodes. While existing analyses primarily focus on spectral mixing properties, they often assume doubly stochastic aggregation, overlooking topology-dependent influence under irregular communication networks. We develop a spectral framework that separates two complementary mechanisms: the dominant eigenmode determines the consensus trajectory and node influence, while non-dominant eigenmodes govern the propagation and attenuation of disagreement. Under uniform neighborhood averaging, we show that the stationary influence is proportional to node degree plus one and derive a bound relating model disagreement to spectral mixing and gradient heterogeneity. We then investigate how these mechanisms interact with the data distribution across nodes. Experiments across regular and heterogeneous network topologies reveal nearly identical learning dynamics under IID data, while network size and connectivity affect how unevenly distributed information is learned under non-IID data. For non-IID settings, we characterize how the distribution of data across nodes shapes the relative contribution of local information to consensus dynamics.

## Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces

DevFeed: [Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces](<https://devfeed.tech/articles/benchmarking-robust-aggregation-in-decentralized-gradient-marketplaces-144856.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2509.05833>)

Author: Zeyu Song, Sainyam Galhotra, Shagufta Mehnaz

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>)

Tags: [adverse-selection](<https://devfeed.tech/tags/adverse-selection.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [contamination](<https://devfeed.tech/tags/contamination.md>), [contributions](<https://devfeed.tech/tags/contributions.md>), [cs-gt](<https://devfeed.tech/tags/cs-gt.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [data-marketplace](<https://devfeed.tech/tags/data-marketplace.md>), [data-products](<https://devfeed.tech/tags/data-products.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decentralized](<https://devfeed.tech/tags/decentralized.md>), [differential-privacy](<https://devfeed.tech/tags/differential-privacy.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [marketplace](<https://devfeed.tech/tags/marketplace.md>), [marketplaces](<https://devfeed.tech/tags/marketplaces.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [model](<https://devfeed.tech/tags/model.md>), [model-performance](<https://devfeed.tech/tags/model-performance.md>), [robust](<https://devfeed.tech/tags/robust.md>)

### AI overview

The benchmark finds that aggregation mechanisms can protect model performance while misallocating payment in gradient data marketplaces. Across a standard baseline and 11 aggregation mechanisms on five vision, text, and tabular datasets, honest high-variance updates were often rejected as outliers while strategically homogeneous malicious updates were accepted and rewarded. The authors report that this adverse selection persists with continuous weight-proportional payment, compounds over repeated rounds as underpaid honest sellers exit, and worsens when differential-privacy noise makes honest updates look contaminated. The framework evaluates mechanism integrity--whether selection and payment reward utility--separately from model integrity.

### Source excerpt

arXiv:2509.05833v2 Announce Type: replace Abstract: Institutions that cannot centralize or sell raw data increasingly exchange model updates instead: cross-silo federated learning is already in production among hospital networks and pharmaceutical consortia. A growing line of research targets the next step: marketplaces in which gradient updates are exchanged as paid, query-specific data products, though none is yet deployed at scale. We formalize this emerging paradigm as a Gradient Data Marketplace (GDM), in which data consumers issue learning tasks and distributed participants contribute query-specific gradient updates. Federated learning asks whether the model survives an attack; a marketplace must also ask who got paid. Existing protocols ensure model-level robustness but fail to capture whether high-quality data is correctly identified and rewarded. In a GDM, selection determines payment, incentivizing participants to optimize for inclusion rather than utility. We introduce a modular benchmarking framework that separates mechanism integrity (whether selection and payment reward true utility) from model integrity, and evaluate a standard baseline alongside 11 widely used aggregation mechanisms on five real-world vision, text, and tabular datasets. Our results reveal consistent adverse selection: honest high-variance contributions are rejected as outliers while strategically homogeneous malicious contributions are accepted and rewarded, even when model performance remains stable. These failures are not artifacts of our accounting: they persist under continuous, weight-proportional payment, compound across repeated market rounds as underpaid honest sellers exit, and worsen when honest sellers add differential-privacy noise, which the filters misread as contamination. Our benchmark provides a foundation for designing incentive-aware, auditable data selection mechanisms in emerging data marketplaces.

## A Byzantine-Robust Federated Learning with Nesterov's Momentum

DevFeed: [A Byzantine-Robust Federated Learning with Nesterov's Momentum](<https://devfeed.tech/articles/a-byzantine-robust-federated-learning-with-nesterov-s-momentum-144863.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2511.02657>)

Author: Lihan Xu, Xiaoyi Fan, Gang Wang, Runhao Zeng, Xiping Hu, Yanjie Dong

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [algorithm](<https://devfeed.tech/tags/algorithm.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [central](<https://devfeed.tech/tags/central.md>), [cifar-10](<https://devfeed.tech/tags/cifar-10.md>), [communication](<https://devfeed.tech/tags/communication.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [convex](<https://devfeed.tech/tags/convex.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [devices](<https://devfeed.tech/tags/devices.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [existing](<https://devfeed.tech/tags/existing.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [faster](<https://devfeed.tech/tags/faster.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [gamma](<https://devfeed.tech/tags/gamma.md>), [momentum](<https://devfeed.tech/tags/momentum.md>), [robust](<https://devfeed.tech/tags/robust.md>)

### AI overview

Byrd-NAFL adds server-side Nesterov momentum to the output of any soft γ-Byzantine-resilient aggregation rule. Workers upload only stochastic gradients, keeping them stateless for intermittent participation. For smooth non-convex losses, the authors prove finite-time convergence for momentum factors β in [0,1) without assuming the aggregated gradient is unbiased or bounded; the bound reduces to Byzantine-resilient SGD at β=0 and is tighter than the stated server-side heavy-ball bound. Experiments on MNIST, CIFAR-10, and Sentiment140 report faster convergence and higher accuracy than existing benchmarks in most tested i.i.d. and non-i.i.d. setups under diverse attacks. Resilience remains limited by the aggregation rule used.

### Source excerpt

arXiv:2511.02657v5 Announce Type: replace Abstract: We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious behaviors. To improve communication efficiency while retaining resilience against such adversaries, we propose a Byzantine-resilient Nesterov-augmented federated learning (Byrd-NAFL) algorithm. Byrd-NAFL applies Nesterov's momentum at the server to the output of any soft $\gamma$-Byzantine resilient aggregation rule, while each worker only computes and uploads a stochastic gradient, which keeps the workers stateless, as desired for intermittently participating Internet of Things devices. For smooth non-convex losses, we establish a finite-time convergence guarantee for all momentum factors $\beta\in[0,1)$ without requiring the aggregated gradient to be unbiased or bounded; the bound reduces to that of Byzantine-resilient stochastic gradient descent at $\beta=0$ and is tighter than that of server-side heavy-ball momentum. Experiments on MNIST, CIFAR-10, and Sentiment140 show that Byrd-NAFL converges faster and attains higher accuracy than existing benchmarks in most i.i.d. and non-i.i.d. setups under diverse attacks, while its resilience is bounded by that of the underlying aggregation rule.

## Federated Learning of Car Aerodynamics Surrogates with Spectral Optimizers

DevFeed: [Federated Learning of Car Aerodynamics Surrogates with Spectral Optimizers](<https://devfeed.tech/articles/federated-learning-of-car-aerodynamics-surrogates-with-spectral-optimizers-145037.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25300>)

Author: Arman Bolatov, Nikolay Spitsyn, Daniil Medyakov, Vladimir Aletov, Dmitry Bylinkin, Martin Tak\\'a\\v{c}, Aleksandr Beznosikov

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

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

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

Tags: [car](<https://devfeed.tech/tags/car.md>), [cfd](<https://devfeed.tech/tags/cfd.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [neural](<https://devfeed.tech/tags/neural.md>)

### AI overview

On DrivAerNet++, FedMuon and the proposed FedMARS-M trained a shared Transolver car-aerodynamics surrogate across six clients to within 2% drag error of centralized training with Muon, using two to four local epochs per round. The study compares these spectral optimizers, which orthogonalize weight-matrix updates, with FedAvg, SCAFFOLD-Adam and FedLion under the same tuning protocol. The non-spectral methods performed best at 16 local epochs, the largest count tested, yet had 17-37% higher drag error than FedMARS-M. The authors link the gap to low stable rank in weight gradients, where an orthogonalized step yielded about twice the first-order decrease of a gradient step with the same spectral norm. The abstract presents this as a way to train across proprietary datasets without exchanging data.

### Source excerpt

arXiv:2611.25300v1 Announce Type: new Abstract: Neural surrogates predict the aerodynamic forces on a car in seconds, compared with hours for a CFD simulation, but training them requires thousands of CFD simulations of different car designs, which car manufacturers keep proprietary. Federated learning allows several manufacturers to train a shared surrogate without exchanging data. We study which federated optimizer brings such a surrogate closest to one trained on pooled data. On DrivAerNet++, we train a Transolver surrogate across six clients that each hold cars of a single body type, and we compare three spectral optimizers, which orthogonalize the update of each weight matrix (FedMuon and two methods we propose, FedMARS-M and FedOLion), with three non-spectral ones (FedAvg, SCAFFOLD-Adam and FedLion), all tuned with the same protocol. FedMuon and FedMARS-M reach a drag error within 2% of centralized training with Muon, using two to four local epochs per round. The non-spectral methods perform best with sixteen local epochs, the largest number we tested, and still have a 17 to 37% higher drag error than FedMARS-M. We relate this gap to the low stable rank of the weight gradients, for which an orthogonalized step yields about twice the first-order decrease of a gradient step of the same spectral norm. Code: https://github.com/armanbolatov/fedmars_drivaernet

## SplitReAlign: Partition-Aware Representation Realignment for Split Federated Unlearning

DevFeed: [SplitReAlign: Partition-Aware Representation Realignment for Split Federated Unlearning](<https://devfeed.tech/articles/splitrealign-partition-aware-representation-realignment-for-split-federated-unlearning-145038.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.25301>)

Author: Jia Chen, Yecheng Lv, Xinrong Hu, Jun Bai

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [all](<https://devfeed.tech/tags/all.md>), [anchor](<https://devfeed.tech/tags/anchor.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [changes](<https://devfeed.tech/tags/changes.md>), [cifar-10](<https://devfeed.tech/tags/cifar-10.md>), [class](<https://devfeed.tech/tags/class.md>), [client](<https://devfeed.tech/tags/client.md>), [clients](<https://devfeed.tech/tags/clients.md>), [coupling](<https://devfeed.tech/tags/coupling.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [distributions](<https://devfeed.tech/tags/distributions.md>), [effectiveness](<https://devfeed.tech/tags/effectiveness.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [feature](<https://devfeed.tech/tags/feature.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [partition](<https://devfeed.tech/tags/partition.md>), [split](<https://devfeed.tech/tags/split.md>)

### AI overview

SplitReAlign addresses class-wise forgetting in split federated learning while aiming to preserve retained utility across heterogeneous client and server representations. It builds endpoint-specific discriminative subspaces around a shared semantic anchor, realigns forgotten representations, and penalizes changes outside those subspaces. Its update strategies reflect partition constraints: Client-only updates use gradients through frozen servers, Server-only guidance uses fixed client-feature statistics, and Joint updates optimize both partitions. On CIFAR-10 and CIFAR-100 with heterogeneous client distributions, it had the lowest average gap to retraining among compared methods across six settings; Server-only was closest to retraining on both datasets. The supplied text reports these results but does not provide numerical gaps or further experimental details.

### Source excerpt

arXiv:2611.25301v1 Announce Type: new Abstract: Split federated learning (SFL) distributes neural networks across clients and a server, coupling class-specific knowledge across their representations. This coupling complicates split federated unlearning (SFU), where class-wise forgetting must remove target knowledge while preserving retained utility under heterogeneous representation spaces and asymmetric update constraints. We propose SplitReAlign, a partition-aware representation realignment framework for class-wise SFU. It constructs endpoint-specific discriminative subspaces coordinated through a shared semantic anchor, selectively realigning forgotten representations while penalizing changes outside the active subspaces. To accommodate asymmetric update constraints, SplitReAlign leverages gradients through frozen servers for Client-only updates and fixed client-feature statistics for Server-only guidance, while Joint updates optimize both partitions. Experiments on CIFAR-10 and CIFAR-100 under heterogeneous client distributions demonstrate that SplitReAlign achieves the lowest average gap to retraining among all compared methods across six settings. Notably, Server-only achieves the closest agreement with retraining on both datasets, highlighting the effectiveness of partition-aware guidance under restricted updates.

## Training-Free Domain Generation for One-Shot Federated Learning with Server-Side Pre-trained Diffusion Models

DevFeed: [Training-Free Domain Generation for One-Shot Federated Learning with Server-Side Pre-trained Diffusion Models](<https://devfeed.tech/articles/training-free-domain-generation-for-one-shot-federated-learning-with-server-side-pre-trained-diffusion-models-142722.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23908>)

Author: Yixuan Tong, Yuanguo Bi, Mingjian Zhi, Wenchao Xu, Yuan Wu

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [ai-image-generator](<https://devfeed.tech/topics/ai-image-generator.md>), [stable-diffusion](<https://devfeed.tech/topics/stable-diffusion.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [adapter](<https://devfeed.tech/tags/adapter.md>), [class](<https://devfeed.tech/tags/class.md>), [classification](<https://devfeed.tech/tags/classification.md>), [classification-accuracy](<https://devfeed.tech/tags/classification-accuracy.md>), [client](<https://devfeed.tech/tags/client.md>), [communication](<https://devfeed.tech/tags/communication.md>), [costs](<https://devfeed.tech/tags/costs.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [data](<https://devfeed.tech/tags/data.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [diffusion-models](<https://devfeed.tech/tags/diffusion-models.md>), [distributions](<https://devfeed.tech/tags/distributions.md>), [domain](<https://devfeed.tech/tags/domain.md>), [domains](<https://devfeed.tech/tags/domains.md>), [encoder](<https://devfeed.tech/tags/encoder.md>), [entropy](<https://devfeed.tech/tags/entropy.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [guidance](<https://devfeed.tech/tags/guidance.md>)

### AI overview

FedDoG addresses heterogeneous client data in one-shot federated learning by using a server-side pre-trained diffusion model to generate domain-aligned synthetic data. Clients send compact domain representations extracted with a frozen image encoder; a pre-trained image-conditioning adapter uses them as visual guidance. The method adjusts conditioning strength based on domain concentration and filters generated samples for class consistency and predictive entropy. On three benchmarks, the authors report higher-quality synthetic images and better classification accuracy than existing OSFL baselines, alongside 99.9% less client upload and 91.5% less client computation time. These are reported experimental results; the excerpt gives no benchmark names or further evaluation details.

### Source excerpt

arXiv:2611.23908v1 Announce Type: new Abstract: One-shot federated learning (OSFL) has attracted increasing attention for its ability to substantially reduce communication overhead by limiting client-server interaction to a single communication round. Nevertheless, this limited interaction makes learning from heterogeneous client distributions challenging. Diffusion-based OSFL approaches seek to address this challenge by synthesizing data that approximate client distributions. However, existing diffusion-based approaches often impose substantial computational costs on clients and lack effective visual guidance to generate data aligned with client distributions. To address these limitations, we propose FedDoG, a training-free Domain Generation framework that leverages server-side pre-trained diffusion models to synthesize data aligned with client domains. FedDoG extracts compact domain representations using a frozen image encoder, substantially reducing client-side computational and communication costs. These representations are incorporated into the diffusion model through a pre-trained image-conditioning adapter, thereby providing explicit visual guidance for domain generation. To further improve the quality of synthetic data, FedDoG adapts the strength of visual conditioning according to domain concentration and filters generated samples based on class consistency and predictive entropy. Experiments on three benchmarks demonstrate that FedDoG generates higher-quality synthetic images and outperforms existing OSFL baselines in classification accuracy. Meanwhile, FedDoG reduces client upload and computation time by 99.9% and 91.5%, respectively. The code is available at https://github.com/YXTong17/FedDoG.

## Same Rank, Different Needs: Rethinking LoRA Redistribution in Federated Learning

DevFeed: [Same Rank, Different Needs: Rethinking LoRA Redistribution in Federated Learning](<https://devfeed.tech/articles/same-rank-different-needs-rethinking-lora-redistribution-in-federated-learning-143440.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23742>)

Author: Jinqian Chen, Jihua Zhu, Chang Liu

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [lora](<https://devfeed.tech/topics/lora.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [learning](<https://devfeed.tech/tags/learning.md>), [lora](<https://devfeed.tech/tags/lora.md>), [rank](<https://devfeed.tech/tags/rank.md>)

### AI overview

In federated LoRA, keeping an aggregated update's leading singular directions may poorly preserve how that update responds to a particular client's inputs. The paper proposes Receiver-Aware Subspace Adaptation (RASA), which uses compact diagonal input second moments to select a rank-constrained readout by uncentered PCA of receiver-weighted responses. The authors report that this readout is optimal for their receiver objective and preserves at least as much response energy as spectral truncation under the diagonal metric. RASA also adds spectral-reference aggregation to remove the personalized initialization offset while retaining the locally learned increment. Experiments across DomainNet-100, NICO++, GLUE, and SuperNI report gains, including 3.23 percentage points in DomainNet-100 accuracy with FlexLoRA and up to 8.33 ROUGE-L points on seen SuperNI tasks and 4.37 on unseen tasks, with modest overhead.

### Source excerpt

arXiv:2611.23742v1 Announce Type: new Abstract: Federated low-rank adaptation (LoRA) enables clients with different resource budgets to collaboratively fine-tune foundation models. To distribute an aggregated update within each client's rank budget, existing methods commonly retain its leading singular directions. However, directions that best reconstruct the update matrix need not best preserve its responses on a particular client's inputs: a lower-energy direction may matter more to that recipient. We formalize this mismatch and show that matrix-optimal truncation can incur arbitrarily larger response error than another readout of the same rank. Motivated by this result, we propose Receiver-Aware Subspace Adaptation (RASA), a plug-in framework for receiver-aware knowledge transfer. RASA uses compact diagonal input second moments to perform uncentered PCA of receiver-weighted update responses. The resulting readout is globally optimal for the rank-constrained receiver objective and preserves at least as much response energy as spectral truncation under the diagonal metric. RASA also introduces spectral-reference aggregation, which removes the personalized initialization offset while retaining the locally learned increment. Experiments on DomainNet-100, NICO++, GLUE, and SuperNI demonstrate RASA's effectiveness across methods under resource, task, and data heterogeneity. In particular, RASA improves DomainNet-100 accuracy by 3.23 percentage points with FlexLoRA and achieves gains of up to 8.33 ROUGE-L points on seen SuperNI tasks and 4.37 on unseen tasks with modest overhead.

## PoCoFL: A Framework for POlicy-COmpliant Federated Learning

DevFeed: [PoCoFL: A Framework for POlicy-COmpliant Federated Learning](<https://devfeed.tech/articles/pocofl-a-framework-for-policy-compliant-federated-learning-143110.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.03650>)

Author: Dominik Roy George, Varesh Mishra, Aysajan Abidin

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [policy-as-code](<https://devfeed.tech/topics/policy-as-code.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [continual-learning](<https://devfeed.tech/tags/continual-learning.md>), [cryptographic](<https://devfeed.tech/tags/cryptographic.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [encrypted](<https://devfeed.tech/tags/encrypted.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [policy](<https://devfeed.tech/tags/policy.md>), [policy-enforcement](<https://devfeed.tech/tags/policy-enforcement.md>), [privacy](<https://devfeed.tech/tags/privacy.md>)

### AI overview

PoCoFL formalizes policy compliance for federated learning by separating the FL setting, policy semantics, and cryptographic implementation. It defines relations for client update admissibility, aggregation correctness, and policy-relative privacy, allowing selected properties of intermediate models or retained state to be checked each round. Clients use compatible cryptographic mechanisms to demonstrate compliant contributions, and aggregators prove that admitted contributions were processed under the chosen aggregation policy. The authors provide formal and proof-of-concept instantiations for vanilla, continual, personalised, and threshold-encrypted FL. They evaluate policy enforcement's effects on learning objectives in the first three settings and measure computational and communication overhead across all four; the abstract gives no numerical results.

### Source excerpt

arXiv:2610.03650v2 Announce Type: replace Abstract: Federated Learning (FL) is a privacy-oriented learning paradigm that enables collaborative model training while keeping training data local to clients. However, FL does not guarantee that clients submit policy-compliant contributions or that aggregators process admitted contributions correctly. Update-magnitude bounds alone cannot ensure compliance with learning-specific requirements involving private data, intermediate models, or retained state. These requirements differ across FL settings, motivating a unified framework to specify and verify client and aggregation policies. This work introduces PoCoFL, a policy-compliant federated learning framework that separates three aspects: (i) FL type, (ii) policy semantics, and (iii) cryptographic realisation. We provide a formalisation that captures client and aggregation requirements as policy-dependent relations, defining update admissibility, aggregation correctness, and policy-relative privacy. These relations enable verification of selected properties of intermediate objects, such as local-model loss, continual-learning state, and personalised optimisation conditions, in each round. Clients demonstrate compliance of their contributions using compatible cryptographic mechanisms, while aggregators prove that the recorded set of admitted contributions was processed according to the selected aggregation policy. We demonstrate PoCoFL through four formal instantiations and corresponding proof-of-concept realisations: (i) vanilla, (ii) continual, (iii) personalised, and (iv) threshold-encrypted federated learning. We evaluate how policy enforcement affects the learning objectives of vanilla, personalised, and continual FL, and quantify the computational and communication overhead of policy verification across all four instantiations. These results demonstrate that PoCoFL captures complex policy representations across the evaluated FL settings.

## FedRAN: Accurate and Efficient Analytic Federated Continual Learning

DevFeed: [FedRAN: Accurate and Efficient Analytic Federated Continual Learning](<https://devfeed.tech/articles/fedran-accurate-and-efficient-analytic-federated-continual-learning-143273.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2606.11480>)

Author: Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan, Rajgopal Kannan, Viktor Prasanna

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

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>), [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>)

Tags: [approximation](<https://devfeed.tech/tags/approximation.md>), [clients](<https://devfeed.tech/tags/clients.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [continual-learning](<https://devfeed.tech/tags/continual-learning.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [dimension](<https://devfeed.tech/tags/dimension.md>), [distributed](<https://devfeed.tech/tags/distributed.md>), [drift](<https://devfeed.tech/tags/drift.md>), [faster](<https://devfeed.tech/tags/faster.md>), [features](<https://devfeed.tech/tags/features.md>), [federated](<https://devfeed.tech/tags/federated.md>), [gram](<https://devfeed.tech/tags/gram.md>), [linear](<https://devfeed.tech/tags/linear.md>), [low-rank](<https://devfeed.tech/tags/low-rank.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [prototype](<https://devfeed.tech/tags/prototype.md>), [rank](<https://devfeed.tech/tags/rank.md>), [structure](<https://devfeed.tech/tags/structure.md>)

### AI overview

FedRAN reduces communication in analytic federated continual learning by compressing second-order information into spectral summaries that can be merged across clients and tasks. Its retained rank controls the tradeoff between approximation fidelity and communication; at fixed rank, second-order communication scales linearly rather than quadratically with feature dimension. Prototype-based pseudo-labeling supports settings with scarce labels. On CIFAR-100, ImageNet-R, and VTAB, the paper reports up to 4.8 percentage points higher average accuracy than the strongest baseline, 30.6-121.8 times less per-client communication, and 190.3 times the speed of optimization-based baselines.

### Source excerpt

arXiv:2606.11480v2 Announce Type: replace Abstract: Federated continual learning (FCL) enables distributed clients to learn from evolving data streams while retaining knowledge from previously observed tasks. Existing optimization-based FCL methods often rely on repeated local training, incurring communication overhead and feature drift across clients. Analytic alternatives avoid iterative training, but high-dimensional random features used to improve accuracy require communicating a Gram matrix whose cost grows quadratically with feature dimension. Communication-efficient alternatives reduce this cost by statistically reconstructing the Gram matrix from first-order summaries. We propose FedRAN, a low-rank analytic FCL framework that instead compresses the required second-order structure directly through spectral summaries that are merged across clients and tasks. The retained rank explicitly controls the tradeoff between approximation fidelity and communication, reducing second-order communication from quadratic to linear in feature dimension for a fixed rank. FedRAN further supports label scarcity through prototype-based pseudo-labeling. Across CIFAR-100, ImageNet-R, and VTAB, FedRAN improves average accuracy by up to 4.8 percentage points over the strongest baseline, uses 30.6-121.8x less per-client communication, and is 190.3x faster than optimization-based baselines.

## Faster to the Wrong Answer: The Price of Local Updates in Federated Optimization

DevFeed: [Faster to the Wrong Answer: The Price of Local Updates in Federated Optimization](<https://devfeed.tech/articles/faster-to-the-wrong-answer-the-price-of-local-updates-in-federated-optimization-143476.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24057>)

Author: Molly Wang

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [bias](<https://devfeed.tech/tags/bias.md>), [client](<https://devfeed.tech/tags/client.md>), [clients](<https://devfeed.tech/tags/clients.md>), [condition-number](<https://devfeed.tech/tags/condition-number.md>), [convex](<https://devfeed.tech/tags/convex.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [eigenvalues](<https://devfeed.tech/tags/eigenvalues.md>), [error](<https://devfeed.tech/tags/error.md>), [federated](<https://devfeed.tech/tags/federated.md>), [filter](<https://devfeed.tech/tags/filter.md>), [global](<https://devfeed.tech/tags/global.md>), [gradient-descent](<https://devfeed.tech/tags/gradient-descent.md>), [hessian](<https://devfeed.tech/tags/hessian.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [objectives](<https://devfeed.tech/tags/objectives.md>), [reduction](<https://devfeed.tech/tags/reduction.md>), [scalar](<https://devfeed.tech/tags/scalar.md>), [sharp](<https://devfeed.tech/tags/sharp.md>)

### AI overview

Local computation in federated optimization can improve conditioning while shifting the updates' fixed point away from the global minimizer. For strongly convex quadratic client objectives with Hessian eigenvalues in [μ,L], the paper gives the exact minimum worst-case bias per unit client heterogeneity under a surrogate condition-number bound χ: (L−μχ)/(2μL√χ). Local gradient descent with sufficiently small step sizes and proximal updates attain this bound. The analysis reduces even arbitrary-dimensional populations with noncommuting Hessians to scalar-curvature distributions, with worst-case constructions using at most three clients. The abstract also reports an extension of the sharp proximal bound to smooth strongly convex nonquadratic objectives and quantifies error from inexact local solves.

### Source excerpt

arXiv:2611.24057v1 Announce Type: new Abstract: Local computation can improve the conditioning of federated updates but may also introduce bias, causing their fixed point to differ from the global minimizer. We characterize the minimum worst-case bias achievable under a prescribed conditioning bound. We consider strongly convex quadratic client objectives with Hessian eigenvalues in $[\mu,L]$ and local updates represented by a shared positive spectral filter. Client heterogeneity is measured by the root-mean-square gradient at the global minimizer. For a uniform surrogate condition number bounded by $\chi\in[1,L/\mu]$, we establish the exact worst-case bias per unit heterogeneity, $(L-\mu\chi)/(2\mu L\sqrt{\chi})$, and show that local gradient descent with sufficiently small step sizes and proximal updates attain this bound. Our analysis reduces populations of arbitrary dimension, including noncommuting Hessians, to distributions over scalar curvatures. This reduction provides optimality certificates and worst-case constructions involving at most three scalar clients. We further extend the sharp proximal bias bound to smooth strongly convex objectives beyond quadratics and quantify the error introduced by inexact local solves.

## 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

## Stealing Exact Training Data from Other Clients during Federated Learning

DevFeed: [Stealing Exact Training Data from Other Clients during Federated Learning](<https://devfeed.tech/articles/stealing-exact-training-data-from-other-clients-during-federated-learning-142985.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24689>)

Author: Omkar Shrikanth, Soham Dambalkar, Parag Jyoti Pal, Advik Raj Basani, Arnab K. Paul

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

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [attack](<https://devfeed.tech/tags/attack.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-privacy](<https://devfeed.tech/tags/data-privacy.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [text](<https://devfeed.tech/tags/text.md>), [training-data](<https://devfeed.tech/tags/training-data.md>)

### AI overview

The proposed attack progressively removes the gradient contributions of sentences it has recovered exactly from a federated-learning aggregate, exposing remaining sentences for recovery in later iterations. The authors report 100% precision for recovered sentences and up to 80.2% exact recovery when aggregates contain up to four times more tokens than the model's hidden dimension; they say existing attacks recover none exactly in that regime. These are reported results from the supplied abstract.

### Source excerpt

arXiv:2611.24689v1 Announce Type: cross Abstract: Malicious adversaries can employ gradient inversion attacks to reverse-engineer private data using the model updates of a round in Federated Learning. While there have been developments in gradient inversion for text, exact text recovery by a malicious client has so far remained infeasible, as FedAvg entangles the gradient contributions of many clients and obscures the signal of any individual sentence. We introduce a novel attack pipeline that unwinds this entanglement progressively through an iterative loop, in which the gradient contributions of sentences recovered exactly in one round are subtracted from the aggregate, exposing the remaining sentences for recovery in the next iteration. We show, for the first time, exact sentence recovery, with 100% precision, and on aggregates containing up to $4\times$ more tokens than the model's hidden dimension, we recover up to 80.2% of client sentences exactly, a regime where existing attacks recover none exactly.

## VAFL: A Vertical Analytic Federated Learning Mechanism for Efficient Crowdsourced Services via Closed-Form Solutions

DevFeed: [VAFL: A Vertical Analytic Federated Learning Mechanism for Efficient Crowdsourced Services via Closed-Form Solutions](<https://devfeed.tech/articles/vafl-a-vertical-analytic-federated-learning-mechanism-for-efficient-crowdsourced-services-via-closed-form-solutions-143514.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24367>)

Author: Yajiang Huang, Anfeng Liu, Tian Wang, Mianxiong Dong, Houbing Herbert Song

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [classification](<https://devfeed.tech/tags/classification.md>), [compression](<https://devfeed.tech/tags/compression.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [regression](<https://devfeed.tech/tags/regression.md>), [services](<https://devfeed.tech/tags/services.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [vertical](<https://devfeed.tech/tags/vertical.md>)

### AI overview

VAFL fits classification and regression heads on fixed local representations using regularized least squares, enabling vertical federated collaboration without pooling raw data. Its agent-assisted protected-computation workflow supports two or multiple parties. A full-dimensional equivalent solve applies block factors directly to the target matrix, avoiding construction of the full inverse. Two width-reduction approaches trade prediction-space compression against retaining local components outside the collaboration subspace: local spectral projection with coefficient lifting, and full-dimensional local fitting with low-rank cross-party correction. Results on five benchmarks report accuracy and training-time tradeoffs and compatibility with diverse frozen backbones; the abstract does not provide detailed measurements.

### Source excerpt

arXiv:2611.24367v1 Announce Type: new Abstract: Intelligent services often rely on complementary information held by different organizations, motivating Vertical Federated Learning without centralized raw-data pooling. We propose VAFL, a Vertical Analytic Federated Learning framework that fits classification and regression heads on fixed local representations through regularized least squares. An agent-assisted protected-computation workflow supports two-party and multi-party collaboration. To reduce fitting overhead, we develop a full-dimensional equivalent solve that applies block factors directly to the target matrix, avoiding construction of the full inverse. We further study two width-reduction strategies: local spectral projection with coefficient lifting, and full-dimensional local fitting with low-rank cross-party correction. The first compresses the prediction space, whereas the second retains local components outside the collaboration subspace. We establish their algebraic properties and analyze their computational scope. Experiments on five benchmarks show the accuracy--cost tradeoffs of these strategies and compatibility with diverse frozen backbones. Predictive performance and training time identify useful operating points and the limits of compression.

## FedE2E: One-Shot Federated Learning for End-to-End Autonomous Driving with Closed-Loop Evaluation

DevFeed: [FedE2E: One-Shot Federated Learning for End-to-End Autonomous Driving with Closed-Loop Evaluation](<https://devfeed.tech/articles/fede2e-one-shot-federated-learning-for-end-to-end-autonomous-driving-with-closed-loop-evaluation-142772.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24254>)

Author: Tao Lian, 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>), [Post-training optimization](<https://devfeed.tech/topics/post-training-optimization.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [autonomous-driving](<https://devfeed.tech/tags/autonomous-driving.md>), [consensus](<https://devfeed.tech/tags/consensus.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [distillation](<https://devfeed.tech/tags/distillation.md>), [end-to-end-autonomous-driving](<https://devfeed.tech/tags/end-to-end-autonomous-driving.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

FedE2E targets end-to-end autonomous driving with one-shot federated learning, where clients collaborate without sharing datasets. It combines multi-client calibration, anchor-based feature alignment, and token-wise consensus distillation to transfer knowledge across heterogeneous models. In closed-loop Bench2Drive evaluation, the method reports a one-shot Driving Score of 55.85, 4.07 points above prior work. With five communication rounds, it reports 60.35, the best score among compared methods at the same round count.

### Source excerpt

arXiv:2611.24254v1 Announce Type: new Abstract: Federated learning enables collaborative model training without sharing datasets. However, existing federated learning methods for autonomous driving typically require multi-round communication and lack closed-loop evaluation, while one-shot methods mainly focus on perception tasks. To address these limitations, we propose \method, a one-shot federated learning method for end-to-end autonomous driving. It comprises multi-client calibration, anchor-based feature alignment, and token-wise consensus distillation to distill knowledge from heterogeneous models. Closed-loop evaluation on Bench2Drive demonstrates the effectiveness of \method in both one-shot and multi-round federated learning. In the one-shot setting, it achieves a Driving Score of 55.85, which is 4.07 points higher than prior work. In the multi-round setting, it reaches 60.35 after five communication rounds, the best performance among all compared methods under the same number of communication rounds.

## Who Pays for Byzantine Robustness? Validity, Data-Share Dictatorships, and Fairness When Only a Few Hospitals Collaborate

DevFeed: [Who Pays for Byzantine Robustness? Validity, Data-Share Dictatorships, and Fairness When Only a Few Hospitals Collaborate](<https://devfeed.tech/articles/who-pays-for-byzantine-robustness-validity-data-share-dictatorships-and-fairness-when-only-a-few-hospitals-collaborate-141501.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22904>)

Author: Adnan Malkani

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-loss](<https://devfeed.tech/tags/data-loss.md>), [data-share](<https://devfeed.tech/tags/data-share.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [fairness](<https://devfeed.tech/tags/fairness.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [hospitals](<https://devfeed.tech/tags/hospitals.md>), [robust](<https://devfeed.tech/tags/robust.md>), [robustness](<https://devfeed.tech/tags/robustness.md>)

### AI overview

The audit finds that Byzantine-robust aggregation rules can behave differently in small, unevenly sized hospital consortia than client-count validity checks suggest. Across three FLamby medical datasets, 54,214 runs, and attacker coalitions of one or two clients, sample-size weighting made median and GeoMed effectively follow a single hospital when it held over half the data; weighted median, GeoMed, and Centered Clipping collapsed when that dominant centre attacked. Exact-twin controls separated honest-data loss from attack damage: on ISIC, losing the largest hospital cost 7.5-10.4 points for count-based rules, while adversarial perturbation accounted for 2.3-3.8 points; weight-dependent rules instead incurred 16.1-25.1 points of attack damage. Unweighted robust rules discounted the institution with the most atypical updates, which was the smallest hospital on Heart but larger institutions on TCGA and ISIC.

### Source excerpt

arXiv:2611.22904v1 Announce Type: cross Abstract: Clinical federated learning (FL) collaborations typically connect only three to six hospitals, yet Byzantine-robust aggregation rules are designed and benchmarked on synthetic partitions across dozens of equal-sized clients. We conduct an empirical audit of eight standard aggregation rules: FedAvg, coordinate-wise median, trimmed mean, Krum, Multi-Krum, Bulyan, geometric median (GeoMed), and Centered Clipping (CC). We evaluate both unweighted and sample-size-weighted variants across three cross-silo medical datasets from the FLamby benchmark: Fed-Heart-Disease ($n = 4$ hospitals), Fed-TCGA-BRCA ($n = 6$ regions), and Fed-ISIC2019 ($n = 6$ centres). We execute 54,214 training runs across enumerated attacker coalitions ($f \in \{1, 2\}$) paired with exact-twin leave-out controls that decompose performance drops into honest data loss versus adversarial attack damage. We report three findings. First, client-count validity checks fail to capture breakdown in skewed medical consortia: while $n = 6, f = 1$ satisfies every count condition except Bulyan's, assigning sample-size weights turns median and GeoMed into a clean-model dictatorship whenever a single hospital holds more than half the training data, and causes weighted median, GeoMed, and CC to collapse when that dominant centre attacks. Second, exact-twin leave-out controls reveal that when the largest hospital attacks, the apparent failure of count-based robust rules is predominantly caused by the loss of honest training data (7.5 to 10.4 points on ISIC) rather than adversarial perturbation (2.3 to 3.8 points on ISIC). Conversely, weight-dependent rules suffer large true attack damage (16.1 to 25.1 points on ISIC). Third, unweighted robust rules consistently discount whichever institution generates the most atypical parameter updates, penalizing the smallest hospital on Heart but penalizing larger institutions on TCGA and ISIC.

## Hierarchical Personalized Federated Learning for Fine-Grained Intrusion Detection: A Multi-Class Analysis in Heterogeneous Attack Environments

DevFeed: [Hierarchical Personalized Federated Learning for Fine-Grained Intrusion Detection: A Multi-Class Analysis in Heterogeneous Attack Environments](<https://devfeed.tech/articles/hierarchical-personalized-federated-learning-for-fine-grained-intrusion-detection-a-multi-class-analysis-in-heterogeneous-attack-environments-141478.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21970>)

Author: Abul Kalam Azad, Travis Atkison

Published: 2026-11-18T05:00:00Z

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>), [NVIDIA Flare](<https://devfeed.tech/topics/nvidia-flare.md>), [threat detection](<https://devfeed.tech/topics/threat-detection.md>), [mlp](<https://devfeed.tech/topics/mlp.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [attack](<https://devfeed.tech/tags/attack.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [intrusion-detection](<https://devfeed.tech/tags/intrusion-detection.md>), [mlp](<https://devfeed.tech/tags/mlp.md>), [nvidia-flare](<https://devfeed.tech/tags/nvidia-flare.md>), [out-of-distribution-generalization](<https://devfeed.tech/tags/out-of-distribution-generalization.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

The abstract reports that hierarchical personalized federated learning (HPFL), combining multi-tier aggregation with client-level personalization, improved fine-grained intrusion detection on CICIDS2017 using MLP models in NVIDIA FLARE. In the 8-class local evaluation, HPFL reached 0.8324 macro F1, above FedAvg (0.7176) and FedProx (0.5624); its micro F1 was 0.9901. Cross-client 4-class micro F1 was 0.9294, compared with 0.9140 for standalone local models. The study also estimates 194.4 MB transmission overhead for HPFL versus 380.3 MB for conventional FL in the 8-class task. These abstract-level results suggest benefits under heterogeneous attack distributions; they do not establish performance beyond the reported dataset and evaluations.

### Source excerpt

arXiv:2611.21970v1 Announce Type: new Abstract: Intrusion Detection Systems (IDS) play a vital role in protecting modern network infrastructures. Although Federated Learning (FL) enables collaborative training without sharing raw network traffic, global models struggle with non-IID attack distributions. Moreover, practical security operations require fine-grained attack classification for targeted threat responses. To address these challenges, this paper investigates the convergence dynamics and performance of Hierarchical Personalized Federated Learning (HPFL), which combines multi-tier aggregation with client-level personalization, for 8-class, 6-class, and 4-class intrusion detection using Multi-Layer Perceptron (MLP) models implemented in NVIDIA FLARE on the CICIDS2017 dataset. Experimental results show that personalized HPFL models achieve micro F1-scores up to 0.9911 in the 6-class task, while the overall local accuracy reaches 0.9975 in the 8-class task. On 8-class local test sets, HPFL achieves a micro F1-score of 0.9901 and a macro F1-score of 0.8324, outperforming FedAvg (0.7176) and FedProx (0.5624) in macro F1. Cross-client evaluations demonstrate out-of-distribution generalization, with HPFL achieving a 4-class micro F1-score of 0.9294 compared with 0.9140 for standalone local models. Furthermore, distance-weighted network analysis estimates a 48.9% reduction in transmission overhead compared with conventional FL (194.4 MB vs. 380.3 MB for the 8-class task). These findings demonstrate HPFLs potential as an accurate, privacy-preserving, and communication-efficient approach to fine-grained intrusion detection in heterogeneous networks.

## CULypso: A Clustered Federated Unlearning paradigm for Vehicular Ad-Hoc Networks

DevFeed: [CULypso: A Clustered Federated Unlearning paradigm for Vehicular Ad-Hoc Networks](<https://devfeed.tech/articles/culypso-a-clustered-federated-unlearning-paradigm-for-vehicular-ad-hoc-networks-140066.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22682>)

Author: Eleftheria Chini, George Margaritis, Dimitrios Katsaros

Published: 2026-11-18T05:00:00Z

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: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [approach](<https://devfeed.tech/tags/approach.md>), [communication](<https://devfeed.tech/tags/communication.md>), [costs](<https://devfeed.tech/tags/costs.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-protection](<https://devfeed.tech/tags/data-protection.md>), [edge](<https://devfeed.tech/tags/edge.md>), [federated](<https://devfeed.tech/tags/federated.md>), [influence](<https://devfeed.tech/tags/influence.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [model](<https://devfeed.tech/tags/model.md>), [networks](<https://devfeed.tech/tags/networks.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [resource](<https://devfeed.tech/tags/resource.md>), [security](<https://devfeed.tech/tags/security.md>), [security-and-privacy](<https://devfeed.tech/tags/security-and-privacy.md>), [server](<https://devfeed.tech/tags/server.md>), [storage](<https://devfeed.tech/tags/storage.md>), [time](<https://devfeed.tech/tags/time.md>), [topology](<https://devfeed.tech/tags/topology.md>)

### AI overview

CULypso proposes approximate hierarchical federated unlearning for clustered vehicular ad-hoc networks (VANETs), using network topology and vehicle movement to reduce communication, resource, and time costs while removing a client's influence on global model updates. The abstract reports experiments in which CULypso performed approximately 65% better than FedEraser on time, server storage load, and unlearning fidelity, and outperformed baseline full retraining. It does not provide detailed algorithm steps or experimental setup in the supplied excerpt.

### Source excerpt

arXiv:2611.22682v1 Announce Type: cross Abstract: Unlearning has emerged as an essential security and privacy-preserving solution in Machine Learning, enabling networks to support their clients' rights for data erasure, as mandated by data protection regulations. Introducing such a non-trivial task to an edge, highly mobile and time-sensitive vehicular network is an even greater, largely unexplored challenge. This article argues that a hierarchical Federated Unlearning approach could be aptly integrated into vehicular ad-hoc networks (VANETs), leveraging topology and movement to reduce communication, resource and time costs, while effectively forgetting a client's influence on the global model updates. In order to achieve this, we propose CULypso, an approximate, surgical, hierarchical unlearning algorithm tailored for clustered VANETs. Inspired by the nymph in Greek mythology, Calypso, whose name translates to 'she who conceals the knowledge', CULypso, with the capital letters referencing \textbf{C}lustered \textbf{U}n\textbf{L}earning, aims to achieve exactly what its name suggests: conceal, erase or forget in our case, knowledge it contains. Extensive experiments uphold the potency of our paradigm with it performing approximately 65\% better than FedEraser in terms of time, server storage load, and unlearning fidelity while utterly outperforming baseline full retraining.

## Projected Penalty-Gradient Tracking for Communication-Efficient Byzantine-Resilient Federated Learning

DevFeed: [Projected Penalty-Gradient Tracking for Communication-Efficient Byzantine-Resilient Federated Learning](<https://devfeed.tech/articles/projected-penalty-gradient-tracking-for-communication-efficient-byzantine-resilient-federated-learning-140095.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.22929>)

Author: Yanjie Dong

Published: 2026-11-18T05:00:00Z

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: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [communication](<https://devfeed.tech/tags/communication.md>), [compression](<https://devfeed.tech/tags/compression.md>), [convex](<https://devfeed.tech/tags/convex.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [error](<https://devfeed.tech/tags/error.md>), [event](<https://devfeed.tech/tags/event.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [fashion](<https://devfeed.tech/tags/fashion.md>), [faster](<https://devfeed.tech/tags/faster.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [gap](<https://devfeed.tech/tags/gap.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [lazy](<https://devfeed.tech/tags/lazy.md>), [local](<https://devfeed.tech/tags/local.md>), [mask](<https://devfeed.tech/tags/mask.md>), [min](<https://devfeed.tech/tags/min.md>), [tracking](<https://devfeed.tech/tags/tracking.md>)

### AI overview

Compressed uploads can undermine penalty-based Byzantine resilience because an adversary may accumulate an unbounded server-side state. The proposed projected penalty-gradient tracking framework has honest workers send compressed residuals and projects reconstructed states onto a known penalty-gradient ball. It supports any contractive compressor and includes FRPG-CS, which protects its shared sparsification mask with freshly drawn reserve rows, and event-triggered LAG-FRPG. For smooth, strongly convex losses, the authors prove a finite-time expected objective-gap bound: the Byzantine error floor is compressor-independent, while compression error decays faster than optimization error. They also bound expected lazy uploads and provide certificates separating finite-penalty model bias from optimization error. On MNIST and Fashion-MNIST, the methods achieved the highest accuracy among twelve methods under Min-Max attack; a compressed-momentum benchmark did better in attack-free accuracy, and a local-update benchmark in total traffic.

### Source excerpt

arXiv:2611.22929v1 Announce Type: cross Abstract: We investigate communication-efficient federated learning over heterogeneous datasets in the presence of Byzantine adversaries capable of uploading arbitrary information. Penalty-based methods bound the influence of each worker through the bounded gradient of a penalty function; however, the bound is lost once the uploads are compressed, since a Byzantine worker can accumulate an unbounded state at the server. To retain the Byzantine resilience under compressed uploads, we propose a projected penalty-gradient tracking framework, where each honest worker uploads a compressed residual of its penalty gradient and the server projects each reconstructed state onto the known penalty-gradient ball. The framework accommodates any contractive compressor and yields two algorithms: fault-resilient proximal gradient with consistent sparsification (FRPG-CS), whose shared mask is protected by freshly drawn reserve rows, and lazily aggregated FRPG (LAG-FRPG), whose uploads are event-triggered. For smooth and strongly convex losses, we establish a finite-time bound on the expected objective gap, where the Byzantine error floor is independent of the compressor and the compression error decays faster than the optimization error. We also bound the expected number of lazy uploads and derive certificates that separate the finite-penalty model bias from the optimization error. Experiments on MNIST and Fashion-MNIST show that the proposed algorithms attain the highest accuracy among twelve methods under the Min-Max attack, whereas a compressed-momentum benchmark and a local-update benchmark remain preferable in attack-free accuracy and total traffic, respectively.

## Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning

DevFeed: [Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning](<https://devfeed.tech/articles/q-localadam-memory-efficient-client-side-adaptive-optimization-for-edge-federated-learning-141562.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.17552>)

Author: Vedant Waykole, Haroon R. Lone

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

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

Topics: [quantization](<https://devfeed.tech/topics/quantization.md>), [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [client](<https://devfeed.tech/tags/client.md>), [compression](<https://devfeed.tech/tags/compression.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [edge](<https://devfeed.tech/tags/edge.md>), [edge-devices](<https://devfeed.tech/tags/edge-devices.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [language](<https://devfeed.tech/tags/language.md>), [latency](<https://devfeed.tech/tags/latency.md>), [linear](<https://devfeed.tech/tags/linear.md>), [memory](<https://devfeed.tech/tags/memory.md>), [momentum](<https://devfeed.tech/tags/momentum.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [size](<https://devfeed.tech/tags/size.md>)

### AI overview

Q-LocalAdam reduces the memory used by client-side adaptive optimizer states in edge federated learning by quantizing the two states differently: block-wise linear quantization for bounded momentum and log-space quantization for heavy-tailed variance. A variance floor after dequantization is used to support numerical stability. The abstract reports convergence close to full-precision training, reduced peak resident memory, and modest quantization latency overhead across human activity, vision, and language workloads, evaluated on physical edge devices and a GPU. It provides no numerical results or detailed comparisons.

### Source excerpt

arXiv:2605.17552v2 Announce Type: replace Abstract: On-device federated learning (FL) on edge devices is limited by the memory required by client-side adaptive optimizers. Maintaining optimizer states locally increases memory usage and can restrict the size of models that can be deployed on resource-constrained edge devices. State quantization can reduce this memory footprint, but uniform compression methods may perform poorly under skewed, non-IID data distributions because they can lose small-variance values that are important for stable optimization. We present \textbf{Q-LocalAdam}, a distribution-aware optimizer for memory-constrained edge devices. It applies block-wise linear quantization to the bounded momentum state and log-space quantization to the heavy-tailed variance state. A post-dequantization variance floor is used to maintain numerical stability. Q-LocalAdam reduces the persistent optimizer-state memory footprint while achieving convergence close to full-precision training. We evaluate Q-LocalAdam on physical edge devices and GPU, measuring persistent optimizer-state storage, process-level memory, and the latency introduced by quantization across human activity, vision, and language workloads. Our results show reduced peak resident memory with modest latency overhead, indicating that distribution-aware state compression can make adaptive optimization practical for edge deployments.

## Federated Dataset Simulation: Inducing Label-Free Heterogeneity Across Tasks

DevFeed: [Federated Dataset Simulation: Inducing Label-Free Heterogeneity Across Tasks](<https://devfeed.tech/articles/federated-dataset-simulation-inducing-label-free-heterogeneity-across-tasks-137517.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.19975>)

Author: Vasilis Siomos, Lam Ngo, Jonathan Passerat-Palmbach, Giacomo Tarroni

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>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [based](<https://devfeed.tech/tags/based.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cast](<https://devfeed.tech/tags/cast.md>), [classification](<https://devfeed.tech/tags/classification.md>), [clients](<https://devfeed.tech/tags/clients.md>), [construction](<https://devfeed.tech/tags/construction.md>), [conversion](<https://devfeed.tech/tags/conversion.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>), [dataset](<https://devfeed.tech/tags/dataset.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [decentralized](<https://devfeed.tech/tags/decentralized.md>), [detection](<https://devfeed.tech/tags/detection.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [federated](<https://devfeed.tech/tags/federated.md>), [free](<https://devfeed.tech/tags/free.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

Federated Dataset Simulation (FDS) addresses the scarcity of real federated benchmarks and the limits of Dirichlet label-skew partitioning, which cannot simulate non-classification tasks such as segmentation and detection. It separates dataset conversion into a representation function and an assignment mechanism, then offers two label-free approaches: geometric partitioning using pretrained model embeddings and semantic partitioning using vision-language model-derived criteria. Across four datasets spanning classification, segmentation, and detection, both approaches induced heterogeneity matching or exceeding label-skew partitioning and measurably affected downstream federated learning performance. The authors release fds, a package for dataset simulation, heterogeneity measurement, and federated training.

### Source excerpt

arXiv:2611.19975v1 Announce Type: cross Abstract: Federated Learning enables collaborative model training across decentralized clients without sharing raw data. While the field has seen rapid growth, the datasets underpinning FL evaluation have not kept pace: real federated datasets remain scarce, and most studies rely on small-scale centralized classification datasets partitioned via Dirichlet label skew, a one-dimensional proxy for the multi-dimensional heterogeneity present in real federations. Moreover, label-based partitioning is by construction inapplicable to non-classification tasks such as segmentation and detection, for which no principled simulation method exists. We cast the conversion of centralized datasets into federated benchmarks as the task of Federated Dataset Simulation (FDS), and decompose it into a representation function $\Phi$ and an assignment mechanism $\pi$. We provide two label-free instantiations -- geometric partitioning via pretrained model embeddings and semantic partitioning via vision-language model-derived criteria -- applicable to classification and dense prediction tasks alike. We evaluate across four datasets spanning classification, segmentation, and detection, and show that both methods induce heterogeneity that matches or exceeds that of label-skew partitioning, with measurable impact on downstream FL performance. We release fds, a modular open-source package for end-to-end federated dataset simulation, heterogeneity measurement, and FL training, at https://github.com/siomvas/fds.

## ExclaveFL: Verifiable Claims for Federated Learning using Exclaves

DevFeed: [ExclaveFL: Verifiable Claims for Federated Learning using Exclaves](<https://devfeed.tech/articles/exclavefl-verifiable-claims-for-federated-learning-using-exclaves-136959.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2412.10537>)

Author: Jinnan Guo, Kapil Vaswani, Andrew Paverd, Peter Pietzuch

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Model Development](<https://devfeed.tech/topics/model-development.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [amd](<https://devfeed.tech/tags/amd.md>), [attestation](<https://devfeed.tech/tags/attestation.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-sanitization](<https://devfeed.tech/tags/data-sanitization.md>), [dataflow](<https://devfeed.tech/tags/dataflow.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [integrity](<https://devfeed.tech/tags/integrity.md>), [model-training](<https://devfeed.tech/tags/model-training.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [proofs](<https://devfeed.tech/tags/proofs.md>), [providers](<https://devfeed.tech/tags/providers.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [security](<https://devfeed.tech/tags/security.md>), [tee](<https://devfeed.tech/tags/tee.md>)

### AI overview

ExclaveFL makes federated-learning claims auditable by attesting data transformations during training. Its integrity-only exclaves produce runtime proofs that form a dataflow graph; an auditor checks the graph for claims such as provider data sanitization and model-provider aggregation. Unlike prior TEE-based systems described in the abstract, the approach does not rely on confidentiality or software-managed secrets, addressing data-leakage attacks against TEE confidentiality. Exclaves require minor proprietary firmware changes, so the authors also evaluate a variant on existing AMD SEV-SNP hardware with similar performance but slightly weaker security guarantees. The abstract reports less than 12% overhead versus unprotected training.

### Source excerpt

arXiv:2412.10537v5 Announce Type: replace-cross Abstract: In federated learning (FL), data providers jointly train a machine learning model without sharing training data. This makes it challenging to provide verifiable claims about the trained model, e.g., related to the employed training data, data sanitization, or training algorithm---a malicious data provider can simply deviate from the correct training protocol without detection. Prior FL training systems have used trusted execution environments (TEEs) to protect the training computation, relying on the confidentiality and integrity of TEEs. TEE confidentiality, however, has been shown to be vulnerable to various attacks, e.g., via side channels. We describe ExclaveFL, a system for training FL models that establishes verifiable claims about models through fine-grained runtime attestation proofs. Since such proofs only require integrity, ExclaveFL generates them using exclaves, which are integrity-only execution environments without software-managed secrets, making them immune to data leakage attacks. ExclaveFL uses exclaves to attest data transformations during FL training, and the runtime attestation proofs then form an attested dataflow graph of the entire training computation. The graph is checked by an auditor to ensure that the trained model satisfies claims, e.g., about the use of data sanitization by data providers or aggregation by the model provider. Since exclaves require minor yet proprietary firmware changes, we evaluate a variant with similar performance but slightly weaker security guarantees on existing AMD SEV-SNP hardware. We show that ExclaveFL introduces less than 12% overhead compared to unprotected FL model training.

## Explainable Federated Learning via Global-Local Attribution Alignment

DevFeed: [Explainable Federated Learning via Global-Local Attribution Alignment](<https://devfeed.tech/articles/explainable-federated-learning-via-global-local-attribution-alignment-137572.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20445>)

Author: Dawood Wasif, Terrence J. Moore, Chang-Tien Lu, Jin-Hee Cho

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>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [alignment](<https://devfeed.tech/tags/alignment.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [attribution](<https://devfeed.tech/tags/attribution.md>), [bandwidth](<https://devfeed.tech/tags/bandwidth.md>), [bandwidth-constraints](<https://devfeed.tech/tags/bandwidth-constraints.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [client](<https://devfeed.tech/tags/client.md>), [clients](<https://devfeed.tech/tags/clients.md>), [communication](<https://devfeed.tech/tags/communication.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>), [device](<https://devfeed.tech/tags/device.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [framework](<https://devfeed.tech/tags/framework.md>), [global](<https://devfeed.tech/tags/global.md>), [image](<https://devfeed.tech/tags/image.md>), [inference](<https://devfeed.tech/tags/inference.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [local](<https://devfeed.tech/tags/local.md>)

### AI overview

xFedAlign coordinates explanations across federated clients while leaving task-model optimization unconstrained. Each client distills a lightweight surrogate to produce private, per-class top-k attribution artifacts; the server robustly aggregates these into a Global Explanation Prior that softly aligns local explanations. The abstract reports FedAvg-matching accuracy across image, text, and tabular IID and non-IID benchmarks, with less explanation drift and better deletion and insertion AUC than Local-XAI, FedAttr-Agg, and Fed-XAI, at a cost of a few kilobytes of extra communication per round. It also reports reduced membership inference advantage and greater resistance to attribution poisoning. These are abstract-level claims; the supplied text does not give detailed evaluation settings or measurements.

### Source excerpt

arXiv:2611.20445v1 Announce Type: cross Abstract: Federated learning enables on-device training without centralizing data, yet existing systems still struggle to provide explanations that are both locally faithful and globally consistent under strict privacy and bandwidth constraints. Prior approaches either keep explanations siloed across clients, transmit heavy or sensitive artifacts, or replace expressive task models with interpretable surrogates that sacrifice accuracy. We propose xFedAlign, a model-agnostic framework that decouples task optimization in parameter space from explanation coordination in a compact group space. Each client distills a lightweight surrogate to produce private, per-class top-k attribution artifacts, which are robustly aggregated by the server into a Global Explanation Prior that softly aligns client explanations without constraining task learning. Across image, text, and tabular benchmarks with IID and non-IID partitions, xFedAlign matches FedAvg accuracy while consistently reducing explanation drift and improving deletion and insertion AUC relative to Local-XAI, FedAttr-Agg, and Fed-XAI, with only a few kilobytes of additional communication per round. Privacy and robustness evaluations further demonstrate reduced membership inference advantage and increased resistance to attribution poisoning, enabling consistent and trustworthy explanations in federated learning.

## NL-SME: Enhancing Multi-Step Gradient Inversion through Adaptive Two-State Matching

DevFeed: [NL-SME: Enhancing Multi-Step Gradient Inversion through Adaptive Two-State Matching](<https://devfeed.tech/articles/nl-sme-enhancing-multi-step-gradient-inversion-through-adaptive-two-state-matching-138722.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2509.22082>)

Author: Li Xia, Jing Yu, Zheng Liu, Sili Huang, Wei Tang, Xuan Liu

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

Content type: article

Language: en

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

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data](<https://devfeed.tech/tags/data.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [hidden](<https://devfeed.tech/tags/hidden.md>), [local](<https://devfeed.tech/tags/local.md>), [matching](<https://devfeed.tech/tags/matching.md>), [mini](<https://devfeed.tech/tags/mini.md>), [model](<https://devfeed.tech/tags/model.md>), [model-training](<https://devfeed.tech/tags/model-training.md>), [models](<https://devfeed.tech/tags/models.md>), [privacy](<https://devfeed.tech/tags/privacy.md>), [private](<https://devfeed.tech/tags/private.md>), [quality](<https://devfeed.tech/tags/quality.md>), [raw](<https://devfeed.tech/tags/raw.md>), [sharing](<https://devfeed.tech/tags/sharing.md>), [sme](<https://devfeed.tech/tags/sme.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

NL-SME reconstructs private data from an individual federated-learning client's endpoint models, assuming the training labels are known. To match updates accumulated over multiple local steps without replaying training, it uses a regularized two-state gradient surrogate: an adaptive evaluation center, regularized displacement, and raw parameter gradients averaged at two shared symmetric states. The abstract reports improved reconstruction quality over existing gradient inversion methods on FEMNIST and CIFAR-100 across varying numbers of local steps, underscoring the privacy risk of sharing individual client updates. It does not provide quantitative results or details of the compared methods.

### Source excerpt

arXiv:2509.22082v4 Announce Type: replace Abstract: Federated learning (FL) enables collaborative model training among multiple clients without directly sharing their raw data.However, gradient inversion attacks can exploit the model updates exchanged during training to reconstruct clients' private data.With multiple local training steps, an observed update combines gradients evaluated at changing model states and potentially different mini-batches, while intermediate states remain hidden. Restricting gradient evaluation to a single state on the segment between the initial and final models can exclude states that better fit the accumulated update.We consider reconstruction from an individual client's endpoint models, assuming that the training labels are known.We propose NL-SME, a regularized two-state gradient surrogate for matching multi-step client updates without replaying local training.The surrogate adapts its evaluation center, regularizes its displacement, and averages raw parameter gradients at two shared symmetric states.We evaluate NL-SME against existing gradient inversion methods on FEMNIST and CIFAR-100 with varying numbers of local training steps.The results show improved reconstruction quality, highlighting the privacy risks of sharing individual client updates after multiple local steps.

## STORMGUIDE-FL: Stochastic Remote Guidance for Efficient Mining of Federated Streaming Data

DevFeed: [STORMGUIDE-FL: Stochastic Remote Guidance for Efficient Mining of Federated Streaming Data](<https://devfeed.tech/articles/stormguide-fl-stochastic-remote-guidance-for-efficient-mining-of-federated-streaming-data-136995.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20975>)

Author: Manuel R\\"oder, Frank-Michael Schleif

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

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>), [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Federated Learning](<https://devfeed.tech/topics/federated-learning.md>), [Data Mining & Modeling](<https://devfeed.tech/topics/data-mining-modeling.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>)

Tags: [acquisition](<https://devfeed.tech/tags/acquisition.md>), [asynchronous](<https://devfeed.tech/tags/asynchronous.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [budget](<https://devfeed.tech/tags/budget.md>), [client](<https://devfeed.tech/tags/client.md>), [clients](<https://devfeed.tech/tags/clients.md>), [compute](<https://devfeed.tech/tags/compute.md>), [concept-drift](<https://devfeed.tech/tags/concept-drift.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [contributions](<https://devfeed.tech/tags/contributions.md>), [convergence](<https://devfeed.tech/tags/convergence.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [data-mining](<https://devfeed.tech/tags/data-mining.md>), [data-privacy](<https://devfeed.tech/tags/data-privacy.md>), [devices](<https://devfeed.tech/tags/devices.md>), [federated](<https://devfeed.tech/tags/federated.md>), [guidance](<https://devfeed.tech/tags/guidance.md>), [mining](<https://devfeed.tech/tags/mining.md>), [remote](<https://devfeed.tech/tags/remote.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [streaming-data](<https://devfeed.tech/tags/streaming-data.md>)

### AI overview

STORMGUIDE-FL targets local concept drift in each client's streaming data and global client drift caused by asynchronous participation and imbalanced contributions. It combines incremental client-side sampling of informative, diverse instances under bounded memory, compute and labeling budgets with server guidance applied as an update-level correction during local optimization. The correction aims to counter client drift without discarding scarce labeled samples. The abstract reports evaluations across gradual, sudden and recurring drift, with sampling gains compounding with the correction and improved speed and robustness of global convergence under resource-constrained, heterogeneous conditions.

### Source excerpt

arXiv:2611.20975v1 Announce Type: cross Abstract: Federated Learning enables collaborative model training across distributed edge devices ("clients") while preserving data privacy. However, real-world deployments involve clients that observe continuous data streams from evolving environments while operating under strict resource limitations. Existing solutions still face two major challenges: local concept drift, where each client's data distribution shifts over time, and global client drift, arising from asynchronous engagement and imbalanced contributions across heterogeneous training participants, formally described as dual client heterogeneity. We propose STORMGUIDE-FL, a federated optimization and data-mining framework that mitigates both types of drift using a server-guided pipeline for data acquisition and local training. For data acquisition, a lightweight client-side sampling strategy incrementally selects informative and diverse instances from non-stationary, non-IID local streams under bounded memory, compute, and labeling budget. For local training, the server's remote guidance is embedded directly into local optimization as an update-level correction, counteracting client drift without discarding scarce labeled samples. We empirically verify the effectiveness of the proposed sampling strategy on federated data streams across gradual, sudden, and recurring concept drift, and demonstrate that its gains compound with the update-level drift correction. Experimental results further show improved speed and robustness of global model convergence under resource-constrained, heterogeneous conditions.

[Next page](<https://devfeed.tech/topics/federated-learning.md?cursor=WyIyMDI2LTExLTE3VDA1OjAwOjAwKzAwOjAwIiwgImQxYzk0ZGM2LWQ3OWItNGEwMS1iNDc1LTgzYTYwMGZhNGUzZCJd>)