Node Classification Beyond Homophily: Towards a General Solution
Open Access
- 4 August 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2862-2873
Abstract
Graph neural networks (GNNs) have become core building blocks behind a myriad of graph learning tasks. The vast majority of the existing GNNs are built upon, either implicitly or explicitly, the homophily assumption, which is not always true and could heavily degrade the performance of learning tasks. In response, GNNs tailored for heterophilic graphs have been developed. However, most of the existing works are designed for the specific GNN models to address heterophily, which lacks generality. In this paper, we study the problem from the structure learning perspective and propose a family of general solutions named ALT. It can work hand in hand with most of the existing GNNs to handle graphs with either low or high homophily. At the core of our method is learning to (1) decompose a given graph into two components, (2) extract complementary graph signals from these two components, and (3) adaptively integrate the graph signals for node classification. Moreover, analysis based on graph signal processing shows that our framework can empower a broad range of existing GNNs to have adaptive filter characteristics and further modulate the input graph signals, which is critical for handling complex homophilic/heterophilic patterns. The proposed ALT brings significant and consistent performance improvement in node classification for a wide range of GNNs over a variety of real-world datasets.Keywords
Funding Information
- NSF (1947135,2134079,1939725)
- DARPA (HR001121C0165)
- NIFA (2020-67021-32799)
- DHS (17STQAC00001-06-00)
- ARO (W911NF2110088)
This publication has 11 references indexed in Scilit:
- Natural and Artificial Dynamics in Graphs: Concept, Progress, and FutureFrontiers in Big Data, 2022
- Data Augmentation for Deep Graph LearningACM SIGKDD Explorations Newsletter, 2022
- Powerful Graph Convolutional Networks with Adaptive Propagation Mechanism for Homophily and HeterophilyProceedings of the AAAI Conference on Artificial Intelligence, 2022
- Graph Sanitation with Application to Node Classification2022
- GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily2022
- Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns2021
- Graph Neural Networks with HeterophilyProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Graph Structure Estimation Neural Networks2021
- Multi-Scale attributed node embeddingJournal of Complex Networks, 2021
- Bayesian Graph Convolutional Neural Networks for Semi-Supervised ClassificationProceedings of the AAAI Conference on Artificial Intelligence, 2019