A Self-Explainable Heterogeneous GNN for Relational Deep Learning

TL;DR

This paper introduces a self-explainable heterogeneous graph neural network that effectively models relational databases by capturing complex meta-path information, outperforming existing methods in accuracy and interpretability.

Contribution

It proposes a novel GNN model that learns from multiple meta-path occurrences without expert supervision, enhancing scalability and interpretability for relational data.

Findings

Outperforms existing methods in synthetic scenarios

Effectively identifies informative meta-paths

Captures model reasoning mechanisms faithfully

Abstract

Recently, significant attention has been given to the idea of viewing relational databases as heterogeneous graphs, enabling the application of graph neural network (GNN) technology for predictive tasks. However, existing GNN methods struggle with the complexity of the heterogeneous graphs induced by databases with numerous tables and relations. Traditional approaches either consider all possible relational meta-paths, thus failing to scale with the number of relations, or rely on domain experts to identify relevant meta-paths. A recent solution does manage to learn informative meta-paths without expert supervision, but assumes that a node's class depends solely on the existence of a meta-path occurrence. In this work, we present a self-explainable heterogeneous GNN for relational data, that supports models in which class membership depends on aggregate information obtained from multiple occurrences of a meta-path. Experimental results show that in the context of relational databases, our approach effectively identifies informative meta-paths that faithfully capture the model's reasoning mechanisms. It significantly outperforms existing methods in both synthetic and real-world scenario.