# Graph Your Own Prompt

DevFeed: [Graph Your Own Prompt](<https://devfeed.tech/articles/graph-your-own-prompt-134948.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2509.23373>)

Author: Xi Ding, Lei Wang, Piotr Koniusz, Yongsheng Gao

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

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

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [class](<https://devfeed.tech/tags/class.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deep](<https://devfeed.tech/tags/deep.md>), [feature](<https://devfeed.tech/tags/feature.md>), [framework](<https://devfeed.tech/tags/framework.md>), [graph](<https://devfeed.tech/tags/graph.md>), [learning](<https://devfeed.tech/tags/learning.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [model](<https://devfeed.tech/tags/model.md>), [model-agnostic](<https://devfeed.tech/tags/model-agnostic.md>), [network](<https://devfeed.tech/tags/network.md>), [novel](<https://devfeed.tech/tags/novel.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [predictions](<https://devfeed.tech/tags/predictions.md>), [prompt](<https://devfeed.tech/tags/prompt.md>)

## AI overview

Graph Consistency Regularization (GCR) aligns feature similarity graphs with class-aware graphs derived from a model's softmax predictions, encouraging feature relationships to reflect predicted class structure. Parameter-free Graph Consistency Layers can be placed at arbitrary network depths; adaptive weighting based on graph discrepancies lets the method emphasize layers with more reliable semantics. The abstract describes GCR as model-agnostic and lightweight, requiring no architecture or training-procedure changes, and reports cleaner feature structure, stronger within-class cohesion, and improved generalization across networks and datasets.

## Source excerpt

arXiv:2509.23373v4 Announce Type: replace-cross Abstract: We propose Graph Consistency Regularization (GCR), a novel framework that injects relational graph structures, derived from model predictions, into the learning process to promote class-aware, semantically meaningful feature representations. Functioning as a form of self-prompting, GCR enables the model to refine its internal structure using its own outputs. While deep networks learn rich representations, these often capture noisy inter-class similarities that contradict the model's predicted semantics. GCR addresses this issue by introducing parameter-free Graph Consistency Layers (GCLs) at arbitrary depths. Each GCL builds a batch-level feature similarity graph and aligns it with a global, class-aware masked prediction graph, derived by modulating softmax prediction similarities with intra-class indicators. This alignment enforces that feature-level relationships reflect class-consistent prediction behavior, acting as a semantic regularizer throughout the network. Unlike prior work, GCR introduces a multi-layer, cross-space graph alignment mechanism with adaptive weighting, where layer importance is learned from graph discrepancy magnitudes. This allows the model to prioritize semantically reliable layers and suppress noisy ones, enhancing feature quality without modifying the architecture or training procedure. GCR is model-agnostic, lightweight, and improves semantic structure across various networks and datasets. Experiments show that GCR promotes cleaner feature structure, stronger intra-class cohesion, and improved generalization, offering a new perspective on learning from prediction structure. [Project website](https://darcyddx.github.io/gcr/) [Code](https://github.com/Darcyddx/graph-prompt)