Contrastive Learning-based Multi-behavior Recommendation with Semantic Knowledge Enhancement

Recently, multi-behavior recommendation has become a hot topic in the field of recommendation systems. Yet, existing methods still face challenges in effectively representing multi-behavior semantic information from the following perspectives: (i) Previous works’ heavy reliance on a unified embedding for modeling all behavior interaction graphs hindered accuratemining of fine-grained user preference semantics across multiple behaviors. (ii) Existing multi-behavior contrastive learning (CL) tasks fail to capture the dependency of user preferring to items under different behaviors, thereby constrains the model’s ability in characterizing the personalized features of users/items. (iii) The rich semantic information in the knowledge graph is not fully leveraged. To address the above challenges, we design a Contrastive Learning-based Multi-behavior Recommendation with Semantic Knowledge Enhancement (CLMRS) framework, which consists of two encoding modules with CL tasks and a joint learning module. Specifically, in the multi-behavior meta-network encoding module, we propose a novel behavior-supervised graph convolutional encoder to fully mine the user preference semantics in each behavior. Meanwhile, in the semantic knowledge enhanced encoding module, we use a knowledge graph to provide more robust embeddings for items. Finally, we integrate the user/item embeddings learned by the two encoding modules into a comprehensive semantic vector through the joint learning module, which is used for the final prediction of potential users. Extensive experiments on four real-world datasets indicate that CLMRS consistently outperforms various state-of-the-art recommendation methods. Our model code is available at https://github.com/yuwenxuan3197/CLMRS.