A Contrastive Collaborative Filtering Method for Personalized Recommendation with Self-Attention
Cheng Yeh Chen, Hao Tian, Hang Zhang, Wanchun Dou · 2024
Recently, sequential and Collaborative Filtering (CF) based recommender systems have shown their research popularity in both academia and industry. Graph-based CF and Transformer-based sequential models have independently shown state-of-art recommendation performance respectively. However, each approach has its own limitation and retrieves different potential factors from users and items. CF aims to retrieve collaborative signals between users and items while Transformer models the temporal dependencies between user historical actions. The under utilization of latent factors can limit the performance and generalization of recommender systems. To address the above limitation, in this paper, we proposed a novel multi-view recommender method called Contrastive Attentive Collaborative Filtering (CACF) that combines collaborative signals and temporal dependencies. Our method leverages the strengths of both approaches by combining the temporal dependecies captured by the Transformer with the user-item collaborative signals retrieved by graph convolutional network (GCN). The Transformer learns temporal dependencies and generates embeddings of items while GCN component capture collaborative signals. By contrastivly optimizing output embeddings from both methods, our approach aims to provide more accurate and personalized recommendations. Finally, we evaluate our method on several benchmark datasets and compare its performance with state-of-the-art recommendation systems. The experimental results show that our method outperforms in several evaluation metrices.