A neural collaborative filtering recommendation algorithm based on attention mechanism and contrastive learning

Abstract The neural collaborative filtering recommendation algorithm widely serves as personalized recommendations of users, which further applies deep learning to a recommendation system. It is a universal framework in the neural collaborative filtering recommendation algorithm; however, it does not regard the impact of important features on recommendation results, nor does it regard the issues of data sparsity and long tail distribution of items. To settle these issues, this article proposes a recommendation algorithm based on the attention mechanism and contrastive learning, which focuses on more important features through the attention mechanism and increases the quantity of samples to achieve data augmentation through contrastive learning; therefore, it enhances recommendation performance. The experimental results on two benchmark datasets show that the algorithm proposed in this article has further enhanced recommendation performance compared to other benchmark algorithms.