HyperSF: A Hypergraph Representation Learning Method Based on Structural Fusion

Abstract

Hypergraph Neural Networks (HNNs) have recently gained attention as a powerful approach for capturing high-order correlations through hypergraph-structured encoding and learning techniques. However, despite their potential, existing HNN methods often encounter over-smoothing issues, which limit their ability to effectively integrate global information while maintaining high-order structural details. This limitation compromises the overall effectiveness of these models. To tackle this challenge, we introduce a novel HNN framework called Hypergraph Structural Fusion (HyperSF). HyperSF combines the structural characteristics of both hypergraphs and graphs to effectively integrate global and local information while preserving the complex high-order structures inherent in hypergraphs. This structural fusion mechanism significantly improves model performance by ensuring that both types of information are utilized in a balanced manner. Comprehensive evaluations show that our method outperforms state-of-the-art approaches, demonstrating its effectiveness in hypergraph representation learning.