Meta-node: A Concise Approach to Effectively Learn Complex Relationships in Heterogeneous Graphs

TL;DR

This paper introduces meta-node, a novel message passing approach for heterogeneous graphs that learns relational knowledge without relying on pre-configured meta-paths or meta-graphs, simplifying the process and improving performance.

Contribution

The paper proposes meta-node, a new concept for message passing in heterogeneous graphs that eliminates the need for expert-designed meta-paths and meta-graphs, enabling more autonomous learning.

Findings

Meta-node outperforms meta-path-based methods in node clustering and classification.

The approach simplifies heterogeneous graph learning by removing pre-processing steps.

Meta-node enhances relational knowledge learning without expert intervention.

Abstract

Existing message passing neural networks for heterogeneous graphs rely on the concepts of meta-paths or meta-graphs due to the intrinsic nature of heterogeneous graphs. However, the meta-paths and meta-graphs need to be pre-configured before learning and are highly dependent on expert knowledge to construct them. To tackle this challenge, we propose a novel concept of meta-node for message passing that can learn enriched relational knowledge from complex heterogeneous graphs without any meta-paths and meta-graphs by explicitly modeling the relations among the same type of nodes. Unlike meta-paths and meta-graphs, meta-nodes do not require any pre-processing steps that require expert knowledge. Going one step further, we propose a meta-node message passing scheme and apply our method to a contrastive learning model. In the experiments on node clustering and classification tasks, the proposed meta-node message passing method outperforms state-of-the-arts that depend on meta-paths. Our results demonstrate that effective heterogeneous graph learning is possible without the need for meta-paths that are frequently used in this field.