Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Anchor-guided Hypergraph Condensation with Dual-level Discrimination

About

The increasing prevalence of large-scale hypergraphs poses significant computational challenges for hypergraph neural network (HNN) training. To address this, hypergraph condensation (HGC) distills large real hypergraphs into compact yet informative synthetic ones, beyond graph condensation (GC) methods limited to pairwise relations. However, existing HGC methods rely on decoupled training architectures, where structure generators are pre-trained on the original hypergraph but not jointly optimized with condensed features during refinement, resulting in misaligned structures that degrade downstream utility. Moreover, trajectory-based optimization incurs substantial computational overhead in refinement, limiting condensation efficiency. To tackle these issues, we propose \textbf{A}nchor-guided \textbf{H}yper\textbf{G}raph \textbf{C}ondensation with \textbf{D}ual-level \textbf{D}iscrimination (\textbf{AHGCDD}), which consists of three key components: (1) a node initialization module based on Heat Kernel PageRank (HKPR) to encode structural knowledge into feature semantics; (2) an anchor-guided hyperedge synthesis strategy for joint optimization of condensed features and structure; (3) a theoretically grounded dual-level discrimination objective for utility-preserving condensation without redundant HNN training. Extensive experiments demonstrate the superior effectiveness and efficiency of AHGCDD.

Fan Li, Xiaoyang Wang, Chen Chen, Wenjie Zhang• 2026

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy77.85
583
Node ClassificationActor
Accuracy72.29
556
Node ClassificationPubmed
Accuracy81.09
363
Node Classificationamazon-ratings
Accuracy25.41
309
Node ClassificationPokec
Accuracy55.04
95
Node ClassificationDBLP CA
Accuracy89.06
62
Node ClassificationWalmart
Accuracy69.09
37
Node ClassificationYelp
Accuracy27.09
35
Node ClassificationMAG-PM
Accuracy58.89
25
Node ClusteringCora r=1% (test)
NMI47.58
4
Showing 10 of 21 rows

Other info

Follow for update