Skip to content

Proactive structural stabilization for robust learning on heterogeneous graphs.

Aug 2026 · Neural Networks · Vol 205 Pt B, pp. 109462 · 0 citations · 48 references
Medicine

TL;DR

This work proposes a proactive structural stabilization framework for robust learning on heterogeneous graphs, termed Proactive STructural stAbilization for roBust LEarning (PSTABLE), and introduces learnable auxiliary nodes along key meta-paths to locally strengthen structural support around vulnerable regions.

Abstract

Heterogeneous graph neural networks capture rich heterogeneous semantics through meta-path modeling, but such semantic propagation may also amplify the prediction instability under structural perturbations. Existing robustness methods are often built upon specific assumptions about perturbation patterns, such as identifying and removing unreliable edges, which limits their generalization when structural perturbations deviate from these assumptions. To address this limitation, we propose a proactive structural stabilization framework for robust learning on heterogeneous graphs, termed Proactive STructural stAbilization for roBust LEarning (PSTABLE). During vulnerability assessment, PSTABLE identifies vulnerable nodes by jointly evaluating structural influence, predictive instability, and semantic participation from complementary perspectives. Based on this analysis, PSTABLE introduces learnable auxiliary nodes along key meta-paths to locally strengthen structural support around vulnerable regions. With model parameters fixed, PSTABLE optimizes auxiliary node representations using the prediction confidence of vulnerable nodes as feedback, thereby enhancing local semantic support while preserving semantic integrity. Extensive experiments under both poisoning and evasion attack settings demonstrate that PSTABLE consistently improves robustness under diverse structural perturbations while maintaining competitive performance on clean graphs.

View source

Similar papers

Conference Open access Sep 2026

Local Geometry Improves Explanation Robustness for Graph Neural Networks

G EO XGNN (Local Geometry Improves Explanation Robustness for Graph Neural Networks), a robust explanation framework that explicitly models the directional sensitivity of structural perturbations from a geometric perspective that significantly improves explanation robustness over existing methods.

Mengting Diao, Li Sun, Sen Su · 0 citations
#artificial intelligence Preprint Aug 2026

NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption

Noise Corruption is introduced, a Noise Corruption-based explanation framework, which perturbs each message through matched-norm random-direction corruption while preserving the expected squared message norm, and NICE, a Noise Corruption-based explanation framework, which learns a Stochastic Restoration Boundary under...

Ziluowen Luo, Jun Yin, Ruo-Chen Liu et al. · 0 citations
Preprint Aug 2026

Subgraph Filtering for Fair Graph Neural Networks

Subgraph Filtering for Fair Graph Neural Networks is proposed, a lightweight and architecture-agnostic framework that mitigates structural bias at its source and achieves consistent fairness improvements while maintaining competitive predictive performance, leading to a better fairness--accuracy trade-off than recent f...

Hao-Hui Lu, Ji-Yuan Tian, Fangyu Zhou et al. · 0 citations
#graph neural networks Open access Sep 2026

Topology-aware GNNs under structural perturbations: Empirical robustness across domains

Results support a conditional empirical conclusion: combining structure, topology, and stability-oriented training can improve robustness under specified structural perturbations, with dataset-dependent accuracy–stability trade-offs rather than universal guarantees.

Jelena Losic, Charles Fanning · 0 citations
Sep 2026

Generalizing on Diverse Shifts: A Unified Topology-Aware Reweighting Algorithm for Graphs.

Topology-Aware Dynamic Reweighting (TAR+), a model-agnostic framework for node classification under strict graph distribution shifts and related robustness stressors, is proposed, supporting the broad applicability of topology-aware reweighting across heterogeneous graph learning conditions.

Jia-Xing Li, Jia-Shuo Liu, Wei-Huang Zheng et al. · 0 citations
Sep 2026

Leveraging Structural Information to Reconstruct Hidden Nodes in Propagation Graphs

Experiments indicate that SHNI is especially useful as an interpretable structural baseline when temporal traces, message content, or network-specific supervised training data are unavailable, and may also be adapted to other propagation phenomena, such as epidemic spread or malware diffusion in computer networks.

Damian Frąszczak · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.