Unveiling the potential of long-range dependence with mask-guided structure learning for hypergraph

Abstract

Hypergraph neural networks have recently drawn widespread attention and have succeeded in many fields. However, existing hypergraph-based neural network approaches are limited to learning local neighborhoods and ignore the representation of long-range dependence. Since the lack of necessary long-range interactions tends to lose critical signals from distant nodes, this paper proposes a new mask-guided hypergraph structure learning (MHSL) method. Specifically, MHSL is comprised of two learning components, i.e., the structure learning component and the initial hypergraph learning component. We design a flexible hypergraph structure learning module in the structure learning component to generate a hypergraph representing the global structure by node stream and hyperedge stream. The initial hypergraph learning component contains the hypergraph convolution that retains the local topological information. Additionally, we design a bidirectional node and hyperedge contrastive learning to learn the consistency between local and global structures. The node classification experiments on the hypergraph datasets demonstrate that the proposed MHSL method achieves competitive performance.