Journal Article

Generating Counterfactual Temporal Motifs: Unraveling the Mysteries of Temporal Graph Neural Networks

Liu, Ning, Li, Qingzhong, Xu, Yonghui, Cui, Lizhen, Zhao, Yibowen

2026

Overview

Temporal Graph Neural Networks (TGNNs) are increasingly applied in dynamic scenarios, however, their limited explainability hinders their adoption in high-stakes domains. Existing methods tend to conflate causality with temporal proximity, leading to ambiguous explanations that mix impactful and irrelevant events. Moreover, they lack counterfactual reasoning to assess whether altering specific temporal events would change TGNN predictions. To overcome these challenges, we propose CTM-Explainer, which identifies critical temporal dependencies through iterative “what-if” perturbation analysis. To the best of our knowledge, this is the first post-hoc counterfactual explanation framework for TGNN. It enables precise attribution of how specific timestamped events influence TGNN predictions. By embedding causal analysis into a reinforcement learning framework, CTM-Explainer constructs Counterfactual Temporal Motifs (CTMs) that are causally grounded in model outcome shifts via interventional probability estimation. This design eliminates temporally correlated but non-essential events, while preserving those with verified causal influence. Extensive experiments on real-world and synthetic datasets confirm that CTM-Explainer generates more faithful and concise explanations than existing methods, at significantly lower computational cost.

• Publisher: Springer Nature Singapore,Springer Nature B.V,SpringerOpen
• Subject: Algorithm Analysis and Problem Complexity / Artificial Intelligence / Chemistry and Earth Sciences / Computer Science / Data Mining and Knowledge Discovery / Database Management / Decision making / Explainable Graph Neural Network / Graph Neural Network / Graph neural networks / Graphs / Neural networks / Perturbation methods / Physics / Post-hoc Explanation / Research Papers / Statistics for Engineering / Synthetic data / Systems and Data Security / Temporal Graph Neural Network