Does Homophily Help in Robust Test-time Node Classification?

2025-10-25

AI Summary

Real-world graph data often suffers from test-time distribution shifts induced by domain shift and temporal evolution, severely compromising the robustness of pre-trained Graph Neural Networks (GNNs) on node classification. This work first reveals that dynamically adapting graph structural homophily at test time—without any model retraining—significantly improves performance. To this end, we propose GrapHoST, a fully test-time, training-free graph structure adaptation method: it employs a lightweight homophily predictor to identify and selectively reweight low-confidence edges, followed by homophily-aware GNN inference. Evaluated across nine benchmark datasets and diverse data degradation scenarios, GrapHoST achieves an average accuracy improvement of 10.92%, substantially outperforming existing robust graph learning approaches.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Homophily, the tendency of nodes from the same class to connect, is a fundamental property of real-world graphs, underpinning structural and semantic patterns in domains such as citation networks and social networks. Existing methods exploit homophily through designing homophily-aware GNN architectures or graph structure learning strategies, yet they primarily focus on GNN learning with training graphs. However, in real-world scenarios, test graphs often suffer from data quality issues and distribution shifts, such as domain shifts across users from different regions in social networks and temporal evolution shifts in citation network graphs collected over varying time periods. These factors significantly compromise the pre-trained model's robustness, resulting in degraded test-time performance. With empirical observations and theoretical analysis, we reveal that transforming the test graph structure by increasing homophily in homophilic graphs or decreasing it in heterophilic graphs can significantly improve the robustness and performance of pre-trained GNNs on node classifications, without requiring model training or update. Motivated by these insights, a novel test-time graph structural transformation method grounded in homophily, named GrapHoST, is proposed. Specifically, a homophily predictor is developed to discriminate test edges, facilitating adaptive test-time graph structural transformation by the confidence of predicted homophily scores. Extensive experiments on nine benchmark datasets under a range of test-time data quality issues demonstrate that GrapHoST consistently achieves state-of-the-art performance, with improvements of up to 10.92%. Our code has been released at https://github.com/YanJiangJerry/GrapHoST.

Problem

• Improving robustness of GNNs on test graphs with data quality issues
• Addressing distribution shifts in test-time node classification tasks
• Enhancing performance through homophily-based graph structural transformation

Innovation

• Transform test graph structure using homophily
• Develop homophily predictor for edge discrimination
• Adapt graph transformation without model retraining