Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
Preprint
Abstract
Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nodes tend to have dissimilar features or labels. While numerous methods have been proposed to address this challenge, they primarily focus on architectural designs without directly targeting the root cause of the heterophily problem. These approaches still perform even worse than the simplest MLPs on challenging heterophilic datasets. For instance, our experiments show that 21 latest GNNs still fall behind the MLP on the Actor dataset. This critical challenge calls for an innovative approach to addressing graph heterophily beyond architectural designs. To bridge this gap, we propose and study a new and unexplored paradigm: directly increasing the graph homophily via a carefully designed graph transformation. In this work, we present a simple yet effective framework called GRAPHITE to address graph heterophily. To the best of our knowledge, this work is the first method that explicitly transforms the graph to directly improve the graph homophily. Stemmed from the exact definition of homophily, our proposed GRAPHITE creates feature nodes to facilitate homophilic message passing between nodes that share similar features. Furthermore, we both theoretically and empirically show that our proposed GRAPHITE significantly increases the homophily of originally heterophilic graphs, with only a slight increase in the graph size. Extensive experiments on challenging datasets demonstrate that our proposed GRAPHITE significantly outperforms state-of-the-art methods on heterophilic graphs while achieving comparable accuracy with state-of-the-art methods on homophilic graphs.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Graph Neural Networks for Graphs With Heterophily: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2026
- A survey on learning from graphs with heterophily: recent advances and future directionsFrontiers of Computer Science, 2025
- On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks2024
- A survey of graph neural network based recommendation in social networksNeurocomputing, 2023
- SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations2023
- DeepRank-GNN: a graph neural network framework to learn patterns in protein–protein interfacesBioinformatics, 2022
- DeepGraphGO: graph neural network for large-scale, multispecies protein function predictionBioinformatics, 2021
- Multi-Scale attributed node embeddingJournal of Complex Networks, 2021