Dual-level Hypergraph Contrastive Learning with Adaptive Temperature Enhancement

Inspired by the success of graph contrastive learning, researchers have begun exploring the benefits of contrastive learning over hypergraphs. However, these works have the following limitations in modeling the high-order relationships over unlabeled data: (i) They primarily focus on maximizing the agreements among individual node embeddings while neglecting the capture of group-wise collective behaviors within hypergraphs; (ii) Most of them disregard the importance of the temperature index in discriminating contrastive pairs during contrast optimization. To address these limitations, we propose a novel dual-level Hy perG raph C ontrastive L earning framework with Ad aptive T emperature (HyGCL-AdT ) to boost contrastive learning over hypergraphs. Specifically, unlike most works that merely maximize the agreement of node embeddings in hypergraphs, we propose a dual-level contrast mechanism that not only captures the individual node behaviors in a local context but also models the group-wise collective behaviors of nodes within hyperedges from a community perspective. Besides, we design an adaptive temperature-enhanced contrastive optimization to improve the discrimination ability between contrastive pairs. Empirical experiments conducted on seven benchmark hypergraphs demonstrate that HyGCL-AdT exhibits excellent effectiveness compared to state-of-the-art baseline models. The source code is available at https://github.com/graphprojects/HyGCL-AdT.