Hypergraph Contrastive Learning
4 papers with code • 1 benchmarks • 1 datasets
Most implemented papers
Augmentations in Hypergraph Contrastive Learning: Fabricated and Generative
This paper targets at improving the generalizability of hypergraph neural networks in the low-label regime, through applying the contrastive learning approach from images/graphs (we refer to it as HyperGCL).
Hypergraph Contrastive Learning for Drug Trafficking Community Detection
To this end, we propose a novel HyperGraph Contrastive Learning framework called HyGCL-DC that employs hypergraph to model the higher-order relationships among users to detect Drug trafficking Communities.
FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling
Specifically, to address the data heterogeneity across domains, we introduce an approach called hypergraph signal decoupling (HSD) to decouple the user features into domain-exclusive and domain-shared features.
Dual-level Hypergraph Contrastive Learning with Adaptive Temperature Enhancement
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.