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

• URL: http://arxiv.org/abs/2605.19822v1
• Date: Tue, 19 May 2026 13:16:22 GMT
• Title: ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
• Abstract summary: Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks.<n>TGNNs fail to identify which historical interactions most influence a given prediction.<n>We propose ST-TGExplainer, a self-explainable TGNN that disentangles Stability and Transition patterns in temporal graphs.
• Score: 61.52935734819602
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Inductive Reasoning for Temporal Knowledge Graphs with Emerging Entities [54.48612448535698]
  Reasoning on Temporal Knowledge Graphs (TKGs) is essential for predicting future events and time-aware facts.<n>We propose TransFIR, a novel framework that leverages historical interaction sequences from semantically similar known entities to support inductive reasoning.
  arXiv  Detail & Related papers  (2026-04-11T11:23:05Z)
• Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck [21.591458816091126]
  Temporal Graph Networks (TGNN) have the ability to capture both the graph topology and dynamic dependencies of interactions within a graph over time. There has been a growing need to explain the predictions of TGNN models due to the difficulty in identifying how past events influence their predictions. This is the first work that simultaneously performs prediction and explanation for temporal graphs in an end-to-end manner.
  arXiv  Detail & Related papers  (2024-06-19T04:55:34Z)
• TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery [15.573944320072284]
  We propose TempME, which uncovers the most pivotal temporal motifs guiding the prediction of temporal graph neural networks (TGNNs) TempME extracts the most interaction-related motifs while minimizing the amount of contained information to preserve the sparsity and succinctness of the explanation. Experiments validate the superiority of TempME, with up to 8.21% increase in terms of explanation accuracy across six real-world datasets and up to 22.96% increase in boosting the prediction Average Precision of current TGNNs.
  arXiv  Detail & Related papers  (2023-10-30T07:51:41Z)
• DyExplainer: Explainable Dynamic Graph Neural Networks [37.16783248212211]
  We present DyExplainer, a novel approach to explaining dynamic Graph Neural Networks (GNNs) on the fly. DyExplainer trains a dynamic GNN backbone to extract representations of the graph at each snapshot. We also augment our approach with contrastive learning techniques to provide priori-guided regularization.
  arXiv  Detail & Related papers  (2023-10-25T05:26:33Z)
• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction [60.60223171143206]
  Trajectory prediction is a crucial undertaking in understanding entity movement or human behavior from observed sequences. Current methods often assume that the observed sequences are complete while ignoring the potential for missing values. This paper presents a unified framework, the Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), which can perform trajectory imputation and prediction simultaneously.
  arXiv  Detail & Related papers  (2023-03-28T14:27:27Z)
• Generic Temporal Reasoning with Differential Analysis and Explanation [61.96034987217583]
  We introduce a novel task named TODAY that bridges the gap with temporal differential analysis. TODAY evaluates whether systems can correctly understand the effect of incremental changes. We show that TODAY's supervision style and explanation annotations can be used in joint learning.
  arXiv  Detail & Related papers  (2022-12-20T17:40:03Z)
• On the Limit of Explaining Black-box Temporal Graph Neural Networks [27.427529601958334]
  Temporal Graph Neural Network (TGNN) has been receiving a lot of attention recently due to its capability in modeling time-evolving graph-related tasks. Similar to Graph Neural Networks, it is also non-trivial to interpret predictions made by a TGNN due to its black-box nature.
  arXiv  Detail & Related papers  (2022-12-02T03:39:57Z)
• Space-Time Graph Neural Networks with Stochastic Graph Perturbations [100.31591011966603]
  Space-time graph neural networks (ST-GNNs) learn efficient graph representations of time-varying data. In this paper we revisit the properties of ST-GNNs and prove that they are stable to graph stabilitys. Our analysis suggests that ST-GNNs are suitable for transfer learning on time-varying graphs.
  arXiv  Detail & Related papers  (2022-10-28T16:59:51Z)
• An Explainer for Temporal Graph Neural Networks [27.393641343203363]
  Temporal graph neural networks (TGNNs) have been widely used for modeling time-evolving graph-related tasks. We propose a novel explainer framework for TGNN models.
  arXiv  Detail & Related papers  (2022-09-02T04:12:40Z)
• Evidential Temporal-aware Graph-based Social Event Detection via Dempster-Shafer Theory [76.4580340399321]
  We propose ETGNN, a novel Evidential Temporal-aware Graph Neural Network. We construct view-specific graphs whose nodes are the texts and edges are determined by several types of shared elements respectively. Considering the view-specific uncertainty, the representations of all views are converted into mass functions through evidential deep learning (EDL) neural networks.
  arXiv  Detail & Related papers  (2022-05-24T16:22:40Z)
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction [69.1473775184952]
  We introduce a realistic problem of few-shot out-of-graph link prediction. We tackle this problem with a novel transductive meta-learning framework. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction.
  arXiv  Detail & Related papers  (2020-06-11T17:42:46Z)

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.