Evolving Graph Contrastive Learning for Socially-aware Recommendation

Social recommendations play a crucial role in providing personalized services to users by leveraging social relationships and user sessions. Despite recent advancements, it still faces challenges in dealing with social inconsistency and the loss of critical semantic information in user-service interactions. To overcome these problems, an Evolving Graph Contrastive Learning for Socially-aware Recommendation (EGCLSR) model is proposed for capturing users’ fresh interests. Specifically, the graph structure features on user-service interactions and the correlations between users and different sequences are extracted by the graph contrastive learning module. Then, social consistency sampling based on the graph convolutional network is adopted to filter out noise information effectively. Finally, time-sliced representations on the dual side (user, service) are integrated to capture users’ evolving interests by employing gated recurrent units. Comprehensive experiments on three datasets demonstrate the proposed model consistently outperforms the representative baseline methods in various evaluation metrics. EGCLSR facilitates the recommendation of services that fulfill instant requirements within dynamically evolving user interests.

I. Introduction

The recommendation systems are dedicated to discovering users’ potential interests and recommending suitable products to them, which are widely applied on various online platforms, such as Amazon and Tmall. In these platforms, the interaction sequences between users and services can be split into multiple sessions at specific time intervals to tap into the user’s interests. As a result, session-based recommendations [1] have emerged to capture the user’s preferences from the session sequences and thus enable prediction of the next item the users may click on.