A Self-Explainable Heterogeneous GNN for Relational Deep Learning
This addresses a bottleneck in relational deep learning for practitioners dealing with complex databases, though it appears incremental as it builds on prior meta-path learning approaches.
The paper tackles the problem of applying graph neural networks to relational databases as heterogeneous graphs, where existing methods struggle with complexity or rely on expert supervision, by proposing a self-explainable GNN that uses aggregate information from multiple meta-path occurrences. Experimental results show it significantly outperforms existing methods in synthetic and real-world scenarios.
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.