Clarify Confused Nodes via Separated Learning
arXiv:2306.02285 · doi:10.1109/TPAMI.2025.3528738
Abstract
Graph neural networks (GNNs) have achieved remarkable advances in graph-oriented tasks. However, real-world graphs invariably contain a certain proportion of heterophilous nodes, challenging the homophily assumption of traditional GNNs and hindering their performance. Most existing studies continue to design generic models with shared weights between heterophilous and homophilous nodes. Despite the incorporation of high-order messages or multi-channel architectures, these efforts often fall short. A minority of studies attempt to train different node groups separately but suffer from inappropriate separation metrics and low efficiency. In this paper, we first propose a new metric, termed Neighborhood Confusion (NC), to facilitate a more reliable separation of nodes. We observe that node groups with different levels of NC values exhibit certain differences in intra-group accuracy and visualized embeddings. These pave the way for Neighborhood Confusion-guided Graph Convolutional Network (NCGCN), in which nodes are grouped by their NC values and accept intra-group weight sharing and message passing. Extensive experiments on both homophilous and heterophilous benchmarks demonstrate that our framework can effectively separate nodes and yield significant performance improvement compared to the latest methods. The source code will be available in https://github.com/GISec-Team/NCGNN.
Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence
References in corpus (28)
- Adam: A Method for Stochastic Optimization
- Pitfalls of Graph Neural Network Evaluation
- Predict then Propagate: Graph Neural Networks meet Personalized PageRank
- Simple and Deep Graph Convolutional Networks
- GraphSAINT: Graph Sampling Based Inductive Learning Method
- Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
- Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
- Diffusion Improves Graph Learning
- Behavior-aware Account De-anonymization on Ethereum Interaction Graph
- Graph Neural Networks for Graphs with Heterophily: A Survey
- Adaptive Universal Generalized PageRank Graph Neural Network
- Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
- Revisiting Heterophily For Graph Neural Networks
- Is Homophily a Necessity for Graph Neural Networks?
- Model Degradation Hinders Deep Graph Neural Networks
- Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation
- Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
- A critical look at the evaluation of GNNs under heterophily: Are we really making progress?
- Time-aware Metapath Feature Augmentation for Ponzi Detection in Ethereum
- Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?
- GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily
- Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
- Graph Neural Networks with Learnable and Optimal Polynomial Bases
- Energy-based Out-of-Distribution Detection for Graph Neural Networks
- Data Augmentation on Graphs: A Technical Survey
- Exphormer: Sparse Transformers for Graphs
- 2-hop Neighbor Class Similarity (2NCS): A graph structural metric indicative of graph neural network performance
- PathMLP: Smooth Path Towards High-order Homophily