HIAL: Towards Semantics-Aware Hypergraph Active Learning via Dual-Perspective Information Maximization

Hypergraph Neural Networks (HNNs) model high-order interactions effectively but rely on costly node annotations, motivating Hypergraph Active Learning (HAL). However, many HAL pipelines adapt graph-based querying through clique expansion, which introduces structural bias and can cause \emph{ranking collapse}, making utilities overly determined by hyperedge cardinalities rather than informative high-order relations. We propose HIAL (Hypergraph Influence-based Active Learning), a training-free framework that reformulates HAL as influence maximization directly on hypergraphs. HIAL employs a High-Order Interaction (HOI)-aware propagation mechanism that modulates influence flow using within-hyperedge feature consistency, capturing both feature sensitivity and topological reachability while preserving HOI semantics. We prove the resulting objective is monotone and submodular, enabling an efficient greedy solver. Experiments on eight benchmarks demonstrate that HIAL consistently outperforms strong baselines across diverse hypergraph domains.