On the Safety of Graph Representation Learning

• URL: http://arxiv.org/abs/2605.06576v1
• Date: Thu, 07 May 2026 17:06:19 GMT
• Title: On the Safety of Graph Representation Learning
• Abstract summary: Graph representation learning (GRL) has evolved from topology-only graph embeddings to task-specific supervised GNNs, and more recently to reusable representations and graph foundation models (GFMs)<n>It remains unclear whether GRL methods stay reliable when deployment stresses affect graph signals, graph contexts, label support, structural groups, or predictive evidence.<n>We introduce GRL-Safety, a multi-axis safety evaluation benchmark for GRL.
• Score: 41.41390553122175
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph representation learning (GRL) has evolved from topology-only graph embeddings to task-specific supervised GNNs, and more recently to reusable representations and graph foundation models (GFMs). However, existing evaluations mainly measure clean transfer, adaptation, and task coverage. It remains unclear whether GRL methods stay reliable when deployment stresses affect graph signals, graph contexts, label support, structural groups, or predictive evidence. We introduce GRL-Safety, a multi-axis safety evaluation benchmark for GRL. GRL-Safety evaluates twelve representative methods, spanning topology-only embedding methods, supervised GNNs, self-supervised graph models, and GFMs, on twenty-five graph datasets under standardized evaluation conditions while preserving method-native adaptation. The evaluation covers five safety axes: corruption robustness, OOD generalization, class imbalance, fairness, and interpretation, with per-axis and sub-condition reporting rather than a single aggregate score. Our analysis yields three cross-axis insights that can inspire future research. First, safety behavior is shaped by the interaction between representation design and the stressed graph factor, rather than by method family alone. Second, foundation-era methods show axis-specific strengths rather than broad safety dominance. Third, several deployment regimes remain difficult even for the best evaluated method, revealing capability gaps that require new robustness, adaptation, or training objectives beyond model selection. The benchmark, evaluation protocols, and code are available at: https://github.com/GXG-CS/GRL-Safety.

Related papers

• Beyond Homophily: Towards Generalized Graph Reconstruction Attack and Defense [80.28330585803133]
  Graph neural networks (GNNs) are widely deployed on computation data, yet they can leak sensitive or proprietary information about the training graph adjacency.<n>This work studies graph reconstruction attacks (GRA), a form of model inversion that reconstructs the training adjacency from a trained GNN.<n>We propose MC-GRA (+), which reconstructs the adjacency by optimizing a surrogate adjacency whose GNN-induced representations align with those of the target model.<n>On the defense side, we propose MC-GPB (+), which suppresses adjacency-dependent information throughout the representation chain
  arXiv  Detail & Related papers  (2026-06-06T09:29:27Z)
• The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning [14.724143004818961]
  In this work, we identify intrinsic geometry as a key latent factor governing model effectiveness.<n>We introduce a curvature-stratified evaluation framework that partitions datasets into positive, negative, and near-zero curvature regimes.<n>We find that model rankings are highly stable within each curvature regime but shift significantly across regimes, indicating that performance is fundamentally geometry-dependent.
  arXiv  Detail & Related papers  (2026-06-04T17:05:36Z)
• Learning to Explore: Policy-Guided Outlier Synthesis for Graph Out-of-Distribution Detection [51.93878677594561]
  In unsupervised graph-level OOD detection, models are typically trained using only in-distribution (ID) data.<n>We propose a Policy-Guided Outlier Synthesis framework that replaces statics with a learned exploration strategy.
  arXiv  Detail & Related papers  (2026-02-28T11:40:18Z)
• G-OSR: A Comprehensive Benchmark for Graph Open-Set Recognition [54.45837774534411]
  We introduce textbfG-OSR, a benchmark for evaluating Graph Open-Set Recognition (GOSR) methods at both the node and graph levels.<n>Results offer critical insights into the generalizability and limitations of current GOSR methods.
  arXiv  Detail & Related papers  (2025-03-01T13:02:47Z)
• Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark [73.58840254552656]
  Unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection have received significant attention in recent years.<n>We present a underlinetextbfUnified underlinetextbfBenchmark for unsupervised underlinetextbfGraph-level underlinetextbfOOD and anomaunderlinetextbfLy underlinetextbfDetection (ourmethod)<n>Our benchmark encompasses 35 datasets
  arXiv  Detail & Related papers  (2024-06-21T04:07:43Z)
• HC-Ref: Hierarchical Constrained Refinement for Robust Adversarial Training of GNNs [7.635985143883581]
  Adversarial training, which has been shown to be one of the most effective defense mechanisms against adversarial attacks in computer vision, holds great promise for enhancing the robustness of GNNs. We propose a hierarchical constraint refinement framework (HC-Ref) that enhances the anti-perturbation capabilities of GNNs and downstream classifiers separately.
  arXiv  Detail & Related papers  (2023-12-08T07:32:56Z)
• Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration [11.709808788756966]
  GraphAC is a principled, task-agnostic, and stable framework for evaluating Graph Neural Network (GNN) research for molecular representation learning. We introduce a novel objective function: the Competitive Barlow Twins, that allow two GNNs to jointly update themselves from direct competitions against each other.
  arXiv  Detail & Related papers  (2023-01-27T03:33:11Z)
• Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learning [24.500868045285287]
  Adversarial attacks on graphs have posed a major threat to the robustness of graph machine learning (GML) models. We present the Graph Robustness Benchmark (GRB) to provide a scalable, unified, modular, and reproducible evaluation for the adversarial robustness of GML models.
  arXiv  Detail & Related papers  (2021-11-08T07:55:13Z)
• Stable Prediction on Graphs with Agnostic Distribution Shift [105.12836224149633]
  Graph neural networks (GNNs) have been shown to be effective on various graph tasks with randomly separated training and testing data. In real applications, however, the distribution of training graph might be different from that of the test one. We propose a novel stable prediction framework for GNNs, which permits both locally and globally stable learning and prediction on graphs.
  arXiv  Detail & Related papers  (2021-10-08T02:45:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.