Heterophily-Aware Representation Learning on Heterogeneous Graphs
- 26 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (9) , 7852-7866
Abstract
Real-world graphs are typically complex, exhibiting heterogeneity in the global structure, as well as strong heterophily within local neighborhoods. While a growing body of literature has revealed the limitations of graph neural networks (GNNs) in handling homogeneous graphs with heterophily, little work has been conducted on investigating the heterophily properties in the context of heterogeneous graphs. To bridge this research gap, we identify the heterophily in heterogeneous graphs using metapaths and propose two practical metrics to quantitatively describe the levels of heterophily. Our empirical investigations on real-world heterogeneous graphs have revealed that heterogeneous graph neural networks (HGNNs), which inherit many mechanisms from GNNs designed for homogeneous graphs, struggle to generalize to heterogeneous graphs with heterophily or low levels of homophily. To address the challenge, we present Hetero$^{2}$ Net, a heterophily-aware HGNN that incorporates masked metapath prediction and masked label prediction tasks to effectively and flexibly handle both homophilic and heterophilic heterogeneous graphs. We evaluate the performance of Hetero$^{2}$ Net on five real-world heterogeneous graph benchmarks with varying levels of heterophily. Experimental results demonstrate that Hetero$^{2}$ Net outperforms strong baselines in the semi-supervised node classification task. In particular, Hetero$^{2}$ Net scales to an industrial-scale commercial graph with 13 M nodes and 157 M edges, demonstrating its effectiveness in handling large and complex heterogeneous graphs.
Keywords
All Related Versions
Funding Information
- National Key R&D Program of China (2022YFF0902500)
- Guangdong Basic and Applied Basic Research Foundation, China (2023A1515011050)
- Shenzhen Science and Technology Program (KJZD20231023094501003)
- Tencent AI Lab (RBFR2024004)
This publication has 30 references indexed in Scilit:
- When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation LearningIEEE Transactions on Neural Networks and Learning Systems, 2025
- When Do We Need Graph Neural Networks for Node Classification?2024
- Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks2022
- A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and SourcesIEEE Transactions on Big Data, 2022
- Adversarial Attack on Large Scale GraphIEEE Transactions on Knowledge and Data Engineering, 2021
- Relation Structure-Aware Heterogeneous Graph Neural Network2019
- Heterogeneous Graph Neural Network2019
- Heterogeneous Graph Attention Network2019
- Modeling Relational Data with Graph Convolutional Networks2018
- metapath2vec2017