Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation

Abstract

Cross-Domain Recommendation (CDR) has been proven to efectively alleviate the data sparsity problem in Recommender System (RS). Recent CDR methods often disentangle user features into domain-invariant and domain-specifc features for efcient cross-domain knowledge transfer. Despite showcasing robust performance, three crucial aspects remain unexplored for existing disentangled CDR approaches:i) The signifcance nuances of the interaction behaviors are ignored in generating disentangled features; ii) The user features are disentangled irrelevant to the individual items to be recommended; iii) The general knowledge transfer overlooks the user’s personality when interacting with diverse items. To this end, we propose a Graph Disentangled Contrastive framework for CDR (GDCCDR) with personalized transfer by meta-networks. An adaptive parameter-free flter is proposed to gauge the signifcance of diverse interactions, thereby facilitating more refned disentangled representations. In sight of the success of Contrastive Learning (CL) in RS, we propose two CL-based constraints for item-aware disentanglement. Proximate CL ensures the coherence of domain-invariant features between domains, while eliminatory CL strives to disentangle features within each domains using mutual information between users and items. Finally, for domain-invariant features, we adopt meta-networks to achieve personalized transfer. Experimental results on four real-world datasets demonstrate the superiority of GDCCDR over state-of-the-art methods.

Liu, Jing, Le-Le Sun, Weizhi Nie, Peiguang Jing, Yuting Su:Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence.Vol. 38. No. 8. 2024.