H$^2$CL: Heterogeneity-Aware Hypergraph Contrastive Learning for Robust Representation

In recent years, hypergraph contrastive learning methods have gained widespread attention due to their excellent performance in processing high-order structural data. However, traditional hypergraph learning method often assume that neighboring nodes are homogeneous, which can lead to the mixing of heterogeneous information in highly heterogeneous datasets, thereby affecting node feature representation. To address this issue, this paper proposes a heterogeneity-sensitive hypergraph contrastive learning method. In the view enhancement stage, we introduce a heterogeneity-aware mechanism that masks high-heterogeneity nodes using hyperedges as intermediaries for information filtering. This mechanism weakens the interference of heterogeneous nodes on view consistency, enabling the model to focus more on key features. In the encoding stage, a heterogeneity-sensitive hypergraph encoder is designed. It dynamically adjusts the weights of information propagation through hyperedges in two phases: node-to-hyperedge" andhyperedge-to-node". This adjustment allows hyperedges to focus on homogeneous information and feedback the aggregated homogeneous information to the respective nodes. Besides, we provide a theoretical proof that our model is capable of aggregating information based on node heterogeneity using hyperedges as intermediate structures. Extensive experimental results demonstrate that this method effectively reduces the interference of heterogeneous information and improves model performance on multiple benchmark datasets. Our code is availabl at: https://anonymous.4open.science/r/HHCL-F926