ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability

TL;DR

ST-TGExplainer is a novel interpretability method for temporal graph neural networks that disentangles stability and transition patterns, providing more faithful explanations while maintaining strong predictive performance.

Contribution

It introduces a self-explainable TGNN model that explicitly separates stability and transition patterns using a disentangled information bottleneck.

Findings

Achieves strong predictive performance on temporal graph tasks.

Provides more faithful and interpretable explanations.

Code is publicly available at the provided GitHub URL.

Abstract

Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks. However, their interpretability remains limited, as most TGNNs fail to identify which historical interactions most influence a given prediction. Despite promising progress on interpretable TGNNs, existing methods predominantly focus on previously seen historical interactions, which we term stability patterns, while overlooking newly emerging first-time interactions, which we term transition patterns. Both types of patterns are essential for faithful temporal explanations. To address this limitation, we propose ST-TGExplainer, a self-explainable TGNN that disentangles Stability and Transition patterns in temporal graphs for a more faithful Temporal GNN Explainer. Guided by a disentangled information bottleneck objective, ST-TGExplainer learns a compact explanatory subgraph that remains predictive of the event label while explicitly suppressing label-conditioned redundancy between stability and transition patterns. Extensive experiments demonstrate that ST-TGExplainer achieves strong predictive performance and yields more faithful explanations. Code is available at https://github.com/hjchen-hdu/ST-TGExplainer.