Task-driven Heterophilic Graph Structure Learning
This addresses a domain-specific challenge in graph learning for heterophilic graphs, offering incremental improvements in node representation learning.
The paper tackles the problem of graph neural networks struggling with heterophilic graphs by proposing FgGSL, an end-to-end framework that learns complementary graph structures and a spectral encoder, achieving consistent outperformance over state-of-the-art methods on six heterophilic benchmarks.
Graph neural networks (GNNs) often struggle to learn discriminative node representations for heterophilic graphs, where connected nodes tend to have dissimilar labels and feature similarity provides weak structural cues. We propose frequency-guided graph structure learning (FgGSL), an end-to-end graph inference framework that jointly learns homophilic and heterophilic graph structures along with a spectral encoder. FgGSL employs a learnable, symmetric, feature-driven masking function to infer said complementary graphs, which are processed using pre-designed low- and high-pass graph filter banks. A label-based structural loss explicitly promotes the recovery of homophilic and heterophilic edges, enabling task-driven graph structure learning. We derive stability bounds for the structural loss and establish robustness guarantees for the filter banks under graph perturbations. Experiments on six heterophilic benchmarks demonstrate that FgGSL consistently outperforms state-of-the-art GNNs and graph rewiring methods, highlighting the benefits of combining frequency information with supervised topology inference.