Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Graph Neural Networks

TL;DR

This paper introduces a novel interpretable causal GNN framework combining retrieval-based causal learning with information bottlenecks, significantly enhancing explanation quality and prediction performance in graph neural networks.

Contribution

It proposes a new framework that couples GNN explanation and prediction using retrieval-based causal learning and Graph Information Bottleneck theory.

Findings

Outperforms state-of-the-art explanation methods

Achieves 32.71% higher explanation precision

Learned explanations improve GNN prediction performance

Abstract

Graph Neural Networks (GNNs) have gained considerable traction for their capability to effectively process topological data, yet their interpretability remains a critical concern. Current interpretation methods are dominated by post-hoc explanations to provide a transparent and intuitive understanding of GNNs. However, they have limited performance in interpreting complicated subgraphs and can't utilize the explanation to advance GNN predictions. On the other hand, transparent GNN models are proposed to capture critical subgraphs. While such methods could improve GNN predictions, they usually don't perform well on explanations. Thus, it is desired for a new strategy to better couple GNN explanation and prediction. In this study, we have developed a novel interpretable causal GNN framework that incorporates retrieval-based causal learning with Graph Information Bottleneck (GIB) theory. The framework could semi-parametrically retrieve crucial subgraphs detected by GIB and compress the explanatory subgraphs via a causal module. The framework was demonstrated to consistently outperform state-of-the-art methods, and to achieve 32.71\% higher precision on real-world explanation scenarios with diverse explanation types. More importantly, the learned explanations were shown able to also improve GNN prediction performance.