Learning Bi-typed Multi-relational Heterogeneous Graph via Dual Hierarchical Attention Networks

TL;DR

This paper introduces DHAN, a dual hierarchical attention network that effectively captures complex structures in bi-typed multi-relational heterogeneous graphs for improved node representation learning.

Contribution

It proposes a novel dual hierarchical attention mechanism that distinguishes intra- and inter-class relations in bi-typed heterogeneous graphs, enhancing structural modeling.

Findings

DHAN outperforms state-of-the-art methods on multiple tasks.

The model effectively captures complex intra- and inter-type relations.

Experimental results validate the superiority of DHAN in node representation learning.

Abstract

Bi-type multi-relational heterogeneous graph (BMHG) is one of the most common graphs in practice, for example, academic networks, e-commerce user behavior graph and enterprise knowledge graph. It is a critical and challenge problem on how to learn the numerical representation for each node to characterize subtle structures. However, most previous studies treat all node relations in BMHG as the same class of relation without distinguishing the different characteristics between the intra-class relations and inter-class relations of the bi-typed nodes, causing the loss of significant structure information. To address this issue, we propose a novel Dual Hierarchical Attention Networks (DHAN) based on the bi-typed multi-relational heterogeneous graphs to learn comprehensive node representations with the intra-class and inter-class attention-based encoder under a hierarchical mechanism. Specifically, the former encoder aggregates information from the same type of nodes, while the latter aggregates node representations from its different types of neighbors. Moreover, to sufficiently model node multi-relational information in BMHG, we adopt a newly proposed hierarchical mechanism. By doing so, the proposed dual hierarchical attention operations enable our model to fully capture the complex structures of the bi-typed multi-relational heterogeneous graphs. Experimental results on various tasks against the state-of-the-arts sufficiently confirm the capability of DHAN in learning node representations on the BMHGs.