Anchor-guided Hypergraph Condensation with Dual-level Discrimination

TL;DR

This paper introduces AHGCDD, a novel hypergraph condensation method that jointly optimizes structure and features using anchor guidance and dual-level discrimination, improving efficiency and utility for hypergraph neural networks.

Contribution

The paper proposes a new hypergraph condensation approach that jointly optimizes structure and features, reducing computational overhead and enhancing downstream utility.

Findings

Outperforms existing methods in effectiveness and efficiency.

Joint optimization improves hypergraph neural network performance.

Dual-level discrimination preserves utility without redundant training.

Abstract

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.