Knowledge-aware recommendations improve performance by using knowledge graphs as auxiliary information. Recently, researchers have introduced the contrastive learning paradigm in knowledge-aware recommendations to enhance representation learning. However, most contrastive learning methods rely on manually or randomly generated knowledge views, making it challenging to generalize to different data distributions and alleviate knowledge noise effects. To solve these issues, we propose a mask diffusion-based contrastive learning method for knowledge-aware recommendation. Specifically, we apply local masked input to the diffusion model, using a mask prediction paradigm to adaptively generate views from both global and local perspectives, thereby enhancing the model's generalization capability across different data distributions. Additionally, we propose a conditional inference process, leveraging user intentions to provide reasonable denoising guidance. At the same time, we design a collaborative knowledge diffusion loss aimed at improving the consistency between generated data and user behavior patterns. In this way, we combine the diffusion model with contrastive learning for the knowledge-aware recommendation, which can improve the generalization ability of the model. Our experimental results on four datasets show the effectiveness of our model. The implementation code is available athttps://github.com/haomiaocqut/ReSys_KMDCL.

Popularity bias is a massive challenge for autoencoder-based models, which decreases the level of personalization and hurts the fairness of recommendations. User reviews reflect their preferences and help mitigate bias or unfairness in the recommendation. However, most existing works typically incorporate user (item) reviews into a long document and then use the same module to process the document in parallel. Actually, the set of user reviews is completely different from the set of item reviews. User reviews are heterogeneous in that they reflect a variety of items purchased by users, while item reviews are only related to the item itself and are thus typically homogeneous. In this article, a novel asymmetric attention network fused with autoencoders is proposed, which jointly learns representations from the user and item reviews and implicit feedback to perform recommendations. Specifically, we design an asymmetric attentive module to capture rich representations from user and item reviews, respectively, which solves data sparsity and explainable problems. Furthermore, to further address popularity bias, we apply a noise-contrastive estimation objective to learn high-quality “de-popularity” embedding via the decoder structure. A series of extensive experiments are conducted on four benchmark datasets to show that leveraging user review information can eliminate popularity bias and improve performance compared to various state-of-the-art recommendation techniques.