Abstract
Graph Neural Networks (GNNs) have demonstrated remarkable success across various graph-related tasks; however, their performance often suffers when dealing with heterophilic graphs, where connected nodes tend to have dissimilar characteristics. This paper introduces a novel approach, Adaptive Neighborhood Feature Mixing (ANFM), that addresses the limitations of traditional GNNs when applied to heterophilic networks. ANFM dynamically learns how to mix feature information from a node's neighborhood based on node and edge attributes. We evaluate the effectiveness of ANFM on several benchmark heterophilic datasets and demonstrate that it outperforms existing state-of-the-art models. Our results highlight the importance of adaptive feature mixing for GNNs operating on complex and heterophilic graph structures.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
"Enhancing Graph Learning via Adaptive Neighborhood Feature Mixing", Technical Disclosure Commons, (January 07, 2025)
https://www.tdcommons.org/dpubs_series/7710