While dynamic graph neural networks have shown promise in various applications, explaining their predictions on continuous-time dynamic graphs (CTDGs) is difficult. This paper investigates a new research task: self-interpretable GNNs for CTDGs. We aim to predict future links within the dynamic graph while simultaneously providing causal explanations for these predictions. There are two key challenges: (1) capturing the underlying structural and temporal information that remains consistent across both independent and identically distributed (IID) and out-of-distribution (OOD) data, and (2) efficiently generating high-quality link prediction results and explanations. To tackle these challenges, we propose a novel causal inference model, namely the Independent and Confounded Causal Model (ICCM). ICCM is then integrated into a deep learning architecture that considers both effectiveness and efficiency. Extensive experiments demonstrate that our proposed model significantly outperforms existing methods across link prediction accuracy, explanation quality, and robustness to shortcut features. Our code and datasets are anonymously released at https://github.com/2024SIG/SIG.
@article{arxiv.2405.19062,
title = {SIG: Efficient Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs},
author = {Lanting Fang and Yulian Yang and Kai Wang and Shanshan Feng and Kaiyu Feng and Jie Gui and Shuliang Wang and Yew-Soon Ong},
journal= {arXiv preprint arXiv:2405.19062},
year = {2024}
}