Repurposing Unified Topological Signatures for Graph Representation Learning
Theoretically, it is shown that integrating UTS into GNN optimization strictly extends GNN expressivity beyond the 1-WL hierarchy, and experiments on three graph classification benchmarks show consistent benefits: Graph-UTS, Dual-UTS, and UTS-Pool improve accuracy across all three datasets, Embedding-UTS provides small...
S. Jain, Anshika Krishnatray, Aditya Sharma et al.
· 0 citations