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.

A Self-Explainable Heterogeneous GNN for Relational Deep Learning / Ferrini, Francesco; Longa, Antonio; Passerini, Andrea; Jaeger, Manfred. - In: TRANSACTIONS ON MACHINE LEARNING RESEARCH. - ISSN 2835-8856. - 02/2025:(2024).

A Self-Explainable Heterogeneous GNN for Relational Deep Learning

Francesco Ferrini;Antonio Longa;Andrea Passerini;Manfred Jaeger
2024-01-01

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.
2024
Ferrini, Francesco; Longa, Antonio; Passerini, Andrea; Jaeger, Manfred
A Self-Explainable Heterogeneous GNN for Relational Deep Learning / Ferrini, Francesco; Longa, Antonio; Passerini, Andrea; Jaeger, Manfred. - In: TRANSACTIONS ON MACHINE LEARNING RESEARCH. - ISSN 2835-8856. - 02/2025:(2024).
File in questo prodotto:
File Dimensione Formato  
3840_A_Self_Explainable_Hetero.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 1.33 MB
Formato Adobe PDF
1.33 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/450430
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact