Abstract
Graph neural networks (GNNs) have shown significant success in learning graph representations. However, recent studies reveal that GNNs often fail to outperform simple MLPs on heterophilous graph tasks, where connected nodes may differ in features or labels, challenging the homophily assumption. Existing methods addressing this issue often overlook the importance of information granularity and rarely consider implicit relationships between distant nodes. To overcome these limitations, we propose the Adaptive Granularity Graph Network (AGGN), a novel GNN model specifically designed for heterophilous graphs. AGGN enhances node embeddings by aggregating multi-view information at various granularity levels and incorporating implicit data from distant, nonneighboring nodes. This approach effectively integrates local and global information, resulting in smoother, more accurate node representations. We also introduce an adaptive graph information aggregator that efficiently combines multi-granularity and implicit data, significantly improving node representation quality, as shown by experiments on 13 datasets covering varying homophily and heterophily. AGGN consistently outperforms 12 state-of-the-art models, excelling on both homophilous and heterophilous graphs.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
"AGGN: Adaptive Granularity Graph Networks for Heterophilic Environments", Technical Disclosure Commons, (May 04, 2025)
https://www.tdcommons.org/dpubs_series/8080