The Same Graph Topology, Three Different Results
TL;DR for operators A graph classifier can use network structure in several ways: supplying structural measurements to the classifier, constraining how representations change during training, or using structure to decide which nodes to retain. These approaches should not be treated as interchangeable. In Repurposing Unified Topological Signatures for Graph Representation Learning, Jain and colleagues1 examine all three using a common Graph Isomorphism Network (GIN) backbone. Their strongest and most consistent results come from adding topological descriptors to graph-level representations. On the ogbg-ppa protein-network benchmark, classification accuracy increases from 67.84% to 71.06%. ...