HERALD: High-Fidelity Exemplar Retrieval with Adaptive Landmark Distillation for Heterophily-Aware Graph Condensation

תקציר מקורי באנגליתarXiv:2609.11123v1 Announce Type: new Abstract: Graph condensation aims to produce a small surrogate graph that preserves the downstream node-classification performance of a much larger original graph. Existing methods rely on Weisfeiler-Lehman neighbourhood aggregation or gradient-based distribution matching, both of which assume that adjacent nodes share the same label, an assumption that breaks down under heterophily. We propose HERALD (High-fidelity Exemplar Retrieval with Adaptive Landmark Distillation), a gradient-free graph condensation framework that adapts the node scoring and feature selection in the condensation pipeline to the graph's measured heterophily. HERALD selects features via a joint Fisher-discriminability and activation-density criterion that down-weights aggregated r