# BHGNN-RT: Capturing bidirectionality and network heterogeneity in graphs

## TL;DR

This paper introduces BHGNN-RT, a new graph neural network method that improves performance on complex, directed graphs by capturing bidirectional and heterogeneous information.

## Contribution

The novel BHGNN-RT model introduces bidirectional message passing, heterogeneous edge handling, and teleportation to enhance learning on directed graphs.

## Key findings

- BHGNN-RT outperforms existing models by up to 11.5% in classification accuracy.
- The model achieves 19.3% improvement in entity clustering on heterogeneous graphs.
- Teleportation and layer optimization significantly enhance model performance.

## Abstract

Graph neural networks (GNNs) have shown great promise for representation learning on complex graph-structured data, but existing models often fall short when applied to directed heterogeneous graphs. In this study, we proposed a novel embedding method, a bidirectional heterogeneous graph neural network with random teleport (BHGNN-RT) that leverages the bidirectional message-passing process and network heterogeneity, for directed heterogeneous graphs. Our method captures both incoming and outgoing message flows, integrates heterogeneous edge types through relation-specific transformations, and introduces a teleportation mechanism to mitigate the oversmoothing effect in deep GNNs. Extensive experiments were conducted on various datasets to verify the efficacy and efficiency of BHGNN-RT. BHGNN-RT consistently outperforms state-of-the-art baselines, achieving up to 11.5% improvement in classification accuracy and 19.3% in entity clustering. Additional analyses confirm that optimizing message components, model layer and teleportation proportion further enhances the model performance. These results demonstrate the effectiveness and robustness of BHGNN-RT in capturing structural, directional information in directed heterogeneous graphs.