Homophily-oriented Heterogeneous Graph Rewiring

Abstract

With the rapid development of the World Wide Web (WWW), heterogeneous graphs (HG) have explosive growth. Recently, heterogeneous graph neural network (HGNN) has shown great potential in learning on HG. Current studies of HGNN mainly focus on some HGs with strong homophily properties (nodes connected by meta-path tend to have the same labels), while few discussions are made in those that are less homophilous. Recently, there have been many works on homogeneous graphs with heterophily. However, due to heterogeneity, it is non-trivial to extend their approach to deal with HGs with heterophily. In this work, based on empirical observations, we propose a meta-path-induced metric to measure the homophily degree of a HG. We also find that current HGNNs may have degenerated performance when handling HGs with less homophilous properties. Thus it is essential to increase the generalization ability of HGNNs on non-homophilous HGs. To this end, we propose HDHGR, a homophily-oriented deep heterogeneous graph rewiring approach that modifies the HG structure to increase the performance of HGNN. We theoretically verify HDHGR. In addition, experiments on real-world HGs demonstrate the effectiveness of HDHGR, which brings at most more than 10% relative gain.

arXiv commentAccepted by WWW 2023

References in corpus (23)

• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• Graph Transformer Networks
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Learning Discrete Structures for Graph Neural Networks
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
• Heterogeneous Global Graph Neural Networks for Personalized Session-based Recommendation
• Efficiently Leveraging Multi-level User Intent for Session-based Recommendation via Atten-Mixer Network
• Graph Neural Networks for Graphs with Heterophily: A Survey
• Multiplex Heterogeneous Graph Convolutional Network
• Learning Multi-granularity User Intent Unit for Session-based Recommendation
• Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendation
• Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks
• Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation
• Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks
• How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications
• Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily
• MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
• Graph Representation Learning Beyond Node and Homophily
• Representation Based Complexity Measures for Predicting Generalization in Deep Learning
• GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily
• Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach

Cited by in corpus (4)

• Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer
• A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
• When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark
• On the Cross-type Homophily of Heterogeneous Graphs: Understanding and Unleashing