Contrastive Hypergraph Flows With Multifaceted Gates for Cross-Domain Sequential Recommendation

Jiajie Su, Xiaolin Zheng, Zibin Lin, Weiming Liu, Chaochao Chen, Jianwei Yin

Abstract: Recommender systems play an important role in various online platforms to provide personalized high-quality service for users. Sequential Recommendation (SR) captures users’ dynamic preferences by modeling their historical interaction sequences, but most SR models suffer performance degradation when meeting with data sparsity problem. To address this issue, we focus on the Cross-Domain Sequential Recommendation (CDSR) service in this article, which aims to exploit and transfer shared sequential patterns across domains to promote the accuracy of single-domain recommendation services. Challenges arise when tackling CDSR, i.e., (1) how to extract intra- and inter-sequence collaborations within domains, (2) how to transfer stable interaction patterns across domains, and (3) how to alleviate data sparsity after integrating cross-domain knowledge. To this end, we propose CHFMG, a contrastive hypergraph flow model with multifaceted gates, which contains two modules, i.e., dual hypergraph flow modeling and multi-view contrastive learning. The first module develops a dual hypergraph flow network to explore dynamic intra- and inter-domain sequential patterns. Innovative multifaceted attentive transfer gates connect local and global hypergraph flow, realizing internal feature fusion and external feature alignment in transfer. The second module achieves contrastive learning from two aspects, i.e., short-term contrasting for retaining sequential pattern consistency and long-term contrasting for enhancing distribution uniformity. Empirical studies on benchmark datasets demonstrate the effectiveness of CHFMG.

External IDs:dblp:journals/tsc/SuZLLCY25