BHGNN-RT: Network embedding for directed heterogeneous graphs

TL;DR

This paper introduces BHGNN-RT, a novel network embedding method for directed heterogeneous graphs that leverages bidirectional message passing and teleportation to improve performance and address over-smoothing.

Contribution

The study proposes BHGNN-RT, a new embedding approach specifically designed for directed heterogeneous graphs, incorporating bidirectional message passing and teleportation optimization.

Findings

BHGNN-RT outperforms baseline methods in node classification.

The method effectively addresses over-smoothing in graph neural networks.

Extensive experiments validate the efficiency and efficacy of BHGNN-RT.

Abstract

Networks are one of the most valuable data structures for modeling problems in the real world. However, the most recent node embedding strategies have focused on undirected graphs, with limited attention to directed graphs, especially directed heterogeneous graphs. In this study, we first investigated the network properties of directed heterogeneous graphs. Based on network analysis, we proposed an embedding method, a bidirectional heterogeneous graph neural network with random teleport (BHGNN-RT), for directed heterogeneous graphs, that leverages bidirectional message-passing process and network heterogeneity. With the optimization of teleport proportion, BHGNN-RT is beneficial to overcome the over-smoothing problem. Extensive experiments on various datasets were conducted to verify the efficacy and efficiency of BHGNN-RT. Furthermore, we investigated the effects of message components, model layer, and teleport proportion on model performance. The performance comparison with all other baselines illustrates that BHGNN-RT achieves state-of-the-art performance, outperforming the benchmark methods in both node classification and unsupervised clustering tasks.