Adaptive Domain Disentanglement and Meta-Contrastive Learning for Knowledge Transfer in Multi-Domain Recommendation

Multi-domain recommendation systems have attracted attention for their potential in utilizing data from various domains. However, existing multi-domain recommendation systems face two limitations. First, current models typically use a unified modeling approach to handle both inter-domain global information (common preferences of users across all domains) and independent intra-domain information (preferences of users within a single domain), leading to the entanglement of the two types of information, making it difficult to effectively utilize them and achieve complementary gains. Second, data sparsity and the lack of effective information transfer mechanisms further limit multi-domain interaction, weakening recommendation performance. To address these limitations, we propose a method that combines adaptive domain disentanglement and multi-domain meta-contrastive learning to disentangle inter-domain and intra-domain information, amplifying the advantages of both types of information to jointly complete the recommendation task. Meanwhile, knowledge transfer between multiple domains is employed to improve overall recommendation performance. To disentangle inter-domain and intra-domain information, we design a shared hypernetwork based on graph convolution to adaptively aggregate neighbor information and inject high-order neighbor information to capture holistic feature. We integrate the meta-learning and contrastive learning. Based on the multi-domain contrastive learning, we design a meta-knowledge encoder and a meta-weight mapping network, generating a tailored loss function that promotes the effective transfer of information between domains. Experiments on three public datasets show our model outperforms nine baseline models.