Existing multi-relational graph neural networks use one of two strategies for identifying informative relations: either they reduce this problem to low-level weight learning, or they rely on handcrafted chains of relational dependencies, called meta-paths. However, the former approach faces challenges in the presence of many relations (e.g., knowledge graphs), while the latter requires substantial domain expertise to identify relevant meta-paths. In this work we propose a novel approach to learn meta-paths and meta-path GNNs that are highly accurate based on a small number of informative meta-paths. Key element of our approach is a scoring function for measuring the potential informativeness of a relation in the incremental construction of the meta-path. Our experimental evaluation shows that the approach manages to correctly identify relevant meta-paths even with a large number of relations, and substantially outperforms existing multi-relational GNNs on synthetic and real-world experiments.

Meta-Path Learning for Multi-relational Graph Neural Networks / Ferrini, Francesco; Longa, Antonio; Passerini, Andrea; Jaeger, Manfred. - 231:(2023), pp. 1-17. (Intervento presentato al convegno LOG 2023 tenutosi a Virtual nel 27th-30th Nov 2023).

Meta-Path Learning for Multi-relational Graph Neural Networks

Ferrini, Francesco
Primo
;
Longa, Antonio
Secondo
;
Passerini, Andrea
Penultimo
;
Jaeger, Manfred
Ultimo
2023-01-01

Abstract

Existing multi-relational graph neural networks use one of two strategies for identifying informative relations: either they reduce this problem to low-level weight learning, or they rely on handcrafted chains of relational dependencies, called meta-paths. However, the former approach faces challenges in the presence of many relations (e.g., knowledge graphs), while the latter requires substantial domain expertise to identify relevant meta-paths. In this work we propose a novel approach to learn meta-paths and meta-path GNNs that are highly accurate based on a small number of informative meta-paths. Key element of our approach is a scoring function for measuring the potential informativeness of a relation in the incremental construction of the meta-path. Our experimental evaluation shows that the approach manages to correctly identify relevant meta-paths even with a large number of relations, and substantially outperforms existing multi-relational GNNs on synthetic and real-world experiments.
2023
Proceedings of the Second Learning on Graphs Conference
SL
SN
Ferrini, Francesco; Longa, Antonio; Passerini, Andrea; Jaeger, Manfred
Meta-Path Learning for Multi-relational Graph Neural Networks / Ferrini, Francesco; Longa, Antonio; Passerini, Andrea; Jaeger, Manfred. - 231:(2023), pp. 1-17. (Intervento presentato al convegno LOG 2023 tenutosi a Virtual nel 27th-30th Nov 2023).
File in questo prodotto:
File Dimensione Formato  
Learning_meta_path_GNN.pdf

accesso aperto

Descrizione: Paper pdf
Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 593.99 kB
Formato Adobe PDF
593.99 kB 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/11572/399994
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact