Automatic Hypergraph Generation for Enhancing Recommendation With Sparse Optimization

• Published in: IEEE transactions on multimedia 2024, Vol.26, p.5680-5693
• Main Authors: Lin, Zhenghong, Yan, Qishan, Liu, Weiming, Wang, Shiping, Wang, Menghan, Tan, Yanchao, Yang, Carl
• Format: Article
• Language: English
• Subjects: Clustering; Collaboration; Collaborative filtering; Combinatorial analysis; Electronic commerce; graph convolutional network; Graph theory; Graphs; hypergraph generation; Multimedia; Noise measurement; Optimization; Recommender systems; Social networking (online); sparse optimization; Task analysis; User satisfaction
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2023.3338083

With the rapid growth of activities on the web, large amounts of interaction data on multimedia platforms are easily accessible, including e-commerce, music sharing, and social media. By discovering various interests of users, recommender systems can improve user satisfaction without accessing overwhelming personal information. Compared to graph-based models, hypergraph-based collaborative filtering has the ability to model higher-order relations besides pair-wise relations among users and items, where the hypergraph structures are mainly obtained from specialized data or external knowledge. However, the above well-constructed hypergraph structures are often not readily available in every situation. To this end, we first propose a novel framework named HGRec, which can enhance recommendation via automatic hypergraph generation. By exploiting the clustering mechanism based on the user/item similarity, we group users and items without additional knowledge for hypergraph structure learning and design a cross-view recommendation module to alleviate the combinatorial gaps between the representations of the local ordinary graph and the global hypergraph. Furthermore, we devise a sparse optimization strategy to ensure the effectiveness of hypergraph structures, where a novel integration of the \ell _{2,1}-norm and optimal transport framework is designed for hypergraph generation. We term the model HGRec with sparse optimization strategy as HGRec++. Extensive experiments on public multi-domain datasets demonstrate the superiority brought by our HGRec++, which gains average 8.1\% and 9.8\% improvement over state-of-the-art baselines regarding Recall and NDCG metrics, respectively.