Service Recommendation Based on Multi-Level View Contrastive Learning

In the context of the rapid development of service-oriented computing and cloud computing, selecting the service that meets the user’s needs from an ever-increasing number of Web services is always challenging. Exploiting auxiliary information such as a Knowledge Graph (KG) can significantly improve the effectiveness of service recommendations. However, current KG-based service recommendation methods usually merely integrate the knowledge semantic information into the user-service interaction model, which ignores the importance of global structure and does not fully consider the in-depth learning of individual user preferences. To this end, this paper proposes a Multi-Level View Contrastive Learning for Service Recommendation (MCSR) approach to address the above challenges. In particular, unlike traditional approaches that consider only two views, we consider three views, i.e., the global structure view, the local collaboration view, and the semantic view. Specifically, the user-service graph is regarded as the collaboration view, the service-entity graph as the semantic view, and the user-service-entity graph as the structural view. By applying contrastive learning across these views at different levels, MCSR fully leverages graph features and structural information, integrating auxiliary relational semantics into user-service interaction modeling. Furthermore, recognizing that the influence of auxiliary information on interactions varies between users and services, a meta-network strategy enables adaptive, personalized knowledge transfer across views, significantly improving recommendation accuracy., since the influence of auxiliary information on interactions varies between users and services, a meta-network strategy enables adaptive, personalized knowledge transfer across views, significantly enhancing recommendation accuracy. The experimental results show that MCSR significantly outperforms current state-of-the-art methods, with the positive impact of its key components on the recommended performance verified by ablation experiments.