Graph Neural Networks with Similarity-Navigated Probabilistic Feature Copying
This addresses fundamental issues in GNNs for graph-based tasks, offering a unified solution for both homophilic and heterophilic graphs, though it appears incremental as it builds on existing GNN paradigms.
The paper tackled the limitations of Graph Neural Networks (GNNs), such as feature oversmoothing and handling heterogeneous relationships, by proposing AxelGNN, which outperformed or matched state-of-the-art methods across diverse graph structures.
Graph Neural Networks (GNNs) have demonstrated remarkable success across various graph-based tasks. However, they face some fundamental limitations: feature oversmoothing can cause node representations to become indistinguishable in deeper networks, they struggle to effectively manage heterogeneous relationships where connected nodes differ significantly, and they process entire feature vectors as indivisible units, which limits flexibility. We seek to address these limitations. We propose AxelGNN, a novel GNN architecture inspired by Axelrod's cultural dissemination model that addresses these limitations through a unified framework. AxelGNN incorporates similarity-gated probabilistic interactions that adaptively promote convergence or divergence based on node similarity, implements trait-level copying mechanisms for fine-grained feature aggregation at the segment level, and maintains global polarization to preserve node distinctiveness across multiple representation clusters. The model's bistable convergence dynamics naturally handle both homophilic and heterophilic graphs within a single architecture. Extensive experiments on node classification and influence estimation benchmarks demonstrate that AxelGNN consistently outperforms or matches state-of-the-art GNN methods across diverse graph structures with varying homophily-heterophily characteristics.