Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
This addresses a limitation in graph learning for heterophilic graphs, which is an incremental improvement over existing aggregation-based methods.
The paper tackles the problem of poor performance of Graph Neural Networks (GNNs) on heterophilic graphs, where connected nodes have different labels, by proposing a simple method using Truncated Singular Value Decomposition (TSVD) of topological structure and node features, achieving up to ~30% improvement over state-of-the-art methods.
Graph Neural Networks (GNNs) have shown excellent performance on graphs that exhibit strong homophily with respect to the node labels i.e. connected nodes have same labels. However, they perform poorly on heterophilic graphs. Recent approaches have typically modified aggregation schemes, designed adaptive graph filters, etc. to address this limitation. In spite of this, the performance on heterophilic graphs can still be poor. We propose a simple alternative method that exploits Truncated Singular Value Decomposition (TSVD) of topological structure and node features. Our approach achieves up to ~30% improvement in performance over state-of-the-art methods on heterophilic graphs. This work is an early investigation into methods that differ from aggregation based approaches. Our experimental results suggest that it might be important to explore other alternatives to aggregation methods for heterophilic setting.