Meta-Path Learning for Multi-relational Graph Neural Networks

Francesco Ferrini, Antonio Longa, Andrea Passerini, Manfred Jaeger

Research output: Contribution to conference without publisher/journalPaper without publisher/journalResearchpeer-review

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.
Original languageEnglish
Publication date2023
Number of pages17
Publication statusPublished - 2023
EventThe Second Learning on Graphs Conference - Online
Duration: 27 Nov 202330 Nov 2023
Conference number: 2
https://logconference.org/

Conference

ConferenceThe Second Learning on Graphs Conference
Number2
LocationOnline
Period27/11/202330/11/2023
Internet address

Fingerprint

Dive into the research topics of 'Meta-Path Learning for Multi-relational Graph Neural Networks'. Together they form a unique fingerprint.

Cite this