2026
Training-free Counterfactual Explanation for Temporal Graph Model Inference
ICLR 2026poster
Temporal graph neural networks (TGNN) extend graph neural networks to dynamic networks and have demonstrated strong predictive power. However, interpreting TGNN remains far less explored than their static-graph counterparts. This paper introduces TEMporal Graph eXplainer (TemGX), a training-free,pos…