Multiplex Heterogeneous Graph Convolutional Network

TL;DR

This paper introduces MHGCN, a novel graph neural network that captures relation heterogeneity and meta-path importance in multiplex heterogeneous networks, improving node embeddings for various analytical tasks.

Contribution

The work proposes a multiplex heterogeneous graph convolutional network that automatically learns meta-path interactions and integrates structural and attribute signals for enhanced embeddings.

Findings

MHGCN outperforms state-of-the-art baselines on multiple datasets.

It effectively captures relation heterogeneity and meta-path importance.

The model improves performance across various network analysis tasks.

Abstract

Heterogeneous graph convolutional networks have gained great popularity in tackling various network analytical tasks on heterogeneous network data, ranging from link prediction to node classification. However, most existing works ignore the relation heterogeneity with multiplex network between multi-typed nodes and different importance of relations in meta-paths for node embedding, which can hardly capture the heterogeneous structure signals across different relations. To tackle this challenge, this work proposes a Multiplex Heterogeneous Graph Convolutional Network (MHGCN) for heterogeneous network embedding. Our MHGCN can automatically learn the useful heterogeneous meta-path interactions of different lengths in multiplex heterogeneous networks through multi-layer convolution aggregation. Additionally, we effectively integrate both multi-relation structural signals and attribute semantics into the learned node embeddings with both unsupervised and semi-supervised learning paradigms. Extensive experiments on five real-world datasets with various network analytical tasks demonstrate the significant superiority of MHGCN against state-of-the-art embedding baselines in terms of all evaluation metrics.