Computer ScienceData Mining and Knowledge Discovery
Multiple hypergraph convolutional network social recommendation using dual contrastive learning
H. Wang, W. Zhou, et al.
Harnessing higher-order social ties and contrastive learning, this paper proposes DCMHS: a dual-objective contrastive learning multiple hypergraph convolution model that builds hypergraphs from social relationships, obtains higher-order user representations via hypergraph convolution, refines them with neighbor and semantic contrastive objectives to avoid aggregation loss, and improves negative sampling using global item embeddings. Experiments on real-world datasets demonstrate the model's effectiveness. Research conducted by Hongyu Wang, Wei Zhou, Junhao Wen, and Shutong Qiao.
Related Publications
Explore these studies to deepen your understanding
Adjacent work that informs or extends this paper's methodology and findings.
Sociology
Social support and reference group: the dual action mechanism of the social network on subjective poverty
S. Li and M. Cai
Medicine and Health
An integrated network representation of multiple cancer-specific data for graph-based machine learning
L. Pu, M. Singha, et al.
Medicine and Health
Convolutional neural network-based classification of glaucoma using optic radiation tissue properties
J. Kruper, A. Richie-halford, et al.
Medicine and Health
Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections
Y. Kim, S. Kim, et al.
