Addressing Graph Heterogeneity and Heterophily from A Spectral Perspective

2024-10-17

AI Summary

This paper addresses the challenging semi-supervised node classification problem on heterogeneous graphs—characterized by multiple node/edge types and strong heterophily (i.e., large attribute or label disparities between adjacent nodes). To this end, we propose H2SGNN, a novel spectral-based graph neural network. Its core contributions are threefold: (1) it is the first method to jointly model heterogeneity and heterophily in the spectral domain; (2) it introduces locally adaptive filters that explicitly capture homophilous or heterophilous patterns along diverse meta-paths; and (3) it incorporates global hybrid filtering to integrate high-order neighborhood information and multi-meta-path semantics. Unlike deep stacking approaches, H2SGNN achieves expressive modeling of complex structural dependencies with a single layer, ensuring both high representational capacity and computational efficiency. Extensive experiments on four standard heterogeneous and heterophilous benchmarks demonstrate state-of-the-art performance, while requiring significantly fewer parameters and lower memory overhead than existing baselines.

Technology Category

Machine Learning: Graph-based Machine LearningData Mining & Knowledge Management: Graph Mining, Social Network Analysis & CommunitySearch and Optimization: Metareasoning and Metaheuristics

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsSearch and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Graph neural networks (GNNs) have demonstrated excellent performance in semi-supervised node classification tasks. Despite this, two primary challenges persist: heterogeneity and heterophily. Each of these two challenges can significantly hinder the performance of GNNs. Heterogeneity refers to a graph with multiple types of nodes or edges, while heterophily refers to the fact that connected nodes are more likely to have dissimilar attributes or labels. Although there have been few works studying heterogeneous heterophilic graphs, they either only consider the heterophily of specific meta-paths and lack expressiveness, or have high expressiveness but fail to exploit high-order neighbors. In this paper, we propose a Heterogeneous Heterophilic Spectral Graph Neural Network (H2SGNN), which employs two modules: local independent filtering and global hybrid filtering. Local independent filtering adaptively learns node representations under different homophily, while global hybrid filtering exploits high-order neighbors to learn more possible meta-paths. Extensive experiments are conducted on four datasets to validate the effectiveness of the proposed H2SGNN, which achieves superior performance with fewer parameters and memory consumption. The code is available at the GitHub repo: https://github.com/Lukangkang123/H2SGNN/.

Problem

• Addressing graph heterogeneity with multiple node/edge types
• Overcoming heterophily where connected nodes differ in attributes
• Improving GNN performance on heterogeneous heterophilic graphs

Innovation

• H2SGNN addresses graph heterogeneity and heterophily
• Uses local independent filtering for node representations
• Employs global hybrid filtering for high-order neighbors