SIG: Efficient Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs

TL;DR

This paper introduces SIG, a self-interpretable graph neural network for continuous-time dynamic graphs that predicts links and provides causal explanations, outperforming existing methods in accuracy, explanation quality, and robustness.

Contribution

The paper proposes a novel causal inference model, ICCM, integrated into a deep learning architecture for efficient, self-interpretable link prediction in CTDGs, addressing structural, temporal, and out-of-distribution challenges.

Findings

Significantly better link prediction accuracy

Higher explanation quality compared to baselines

Robustness to shortcut features demonstrated

Abstract

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.