Meta-Path Learning for Multi-relational Graph Neural Networks
This addresses the problem of requiring domain expertise or facing scalability issues in multi-relational graphs like knowledge graphs, offering a more automated solution.
The paper tackles the challenge of identifying informative relations in multi-relational graph neural networks by proposing a novel approach to learn meta-paths and meta-path GNNs, which substantially outperforms existing methods on synthetic and real-world experiments.
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.