Meta-Path Learning for Multi-relational Graph Neural Networks

TL;DR

This paper introduces a novel method for learning meta-paths in multi-relational graph neural networks, enabling high accuracy with fewer meta-paths and outperforming existing methods on synthetic and real data.

Contribution

A new approach to automatically learn informative meta-paths using a scoring function, reducing reliance on domain expertise and improving performance.

Findings

Successfully identifies relevant meta-paths in large relation sets

Outperforms existing multi-relational GNNs on benchmarks

Effective in both synthetic and real-world scenarios

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.