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

arXiv: https://arxiv.org/abs/2605.19822 · HTML: https://mlsanity.com/paper/2605.19822/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 49 references that are in the map.
- First posted on arXiv 19 May 2026.

## Builds on (most cited first, 30 of 32)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Graph Neural Networks for Graphs with Heterophily: A Survey](https://mlsanity.com/paper/2202.07082/) (2022)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Higher-Order Explanations of Graph Neural Networks via Relevant Walks](https://mlsanity.com/paper/2006.03589/) (2020)
- [Temporal Graph Benchmark for Machine Learning on Temporal Graphs](https://mlsanity.com/paper/2307.01026/) (2023)
- [Towards Better Evaluation for Dynamic Link Prediction](https://mlsanity.com/paper/2207.10128/) (2022)
- [ProtGNN: Towards Self-Explaining Graph Neural Networks](https://mlsanity.com/paper/2112.00911/) (2021)
- [TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery](https://mlsanity.com/paper/2310.19324/) (2023)
- [Interpretable Prototype-based Graph Information Bottleneck](https://mlsanity.com/paper/2310.19906/) (2023)
- [Temporal Link Prediction: A Unified Framework, Taxonomy, and Review](https://mlsanity.com/paper/2210.08765/) (2022)
- [TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics](https://mlsanity.com/paper/2502.02975/) (2025)
- [Repeat-Aware Neighbor Sampling for Dynamic Graph Learning](https://mlsanity.com/paper/2405.17473/) (2024)
- [Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck](https://mlsanity.com/paper/2406.13214/) (2024)
- [Temporal Graph Representation Learning with Adaptive Augmentation Contrastive](https://mlsanity.com/paper/2311.03897/) (2023)
- [A Differential Geometric View and Explainability of GNN on Evolving Graphs](https://mlsanity.com/paper/2403.06425/) (2024)
- [A Survey on Temporal Interaction Graph Representation Learning: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2505.04461/) (2025)
- [Multiscale Dynamic Graph Representation for Biometric Recognition with Occlusions](https://mlsanity.com/paper/2307.14617/) (2023)
- [Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning](https://mlsanity.com/paper/2512.10573/) (2025)
- [Are We Really Achieving Better Beyond-Accuracy Performance in Next Basket Recommendation?](https://mlsanity.com/paper/2405.01143/) (2024)
- [Heterogeneous Temporal Hypergraph Neural Network](https://mlsanity.com/paper/2506.17312/) (2025)

## Abstract (arXiv)

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.