Fuzzy clustering-based dual-channel contrastive learning for multi-behavior recommendation

In recommender systems, diverse user behaviors (e.g., clicking, purchasing, sharing) provide valuable insights into user preferences. While multi-behavior recommendation models have shown promise, existing models often suffer from excessive complexity or fail to effectively capture relationships between behaviors. Two major challenges persist: (1) Most models focus primarily on user–item interactions, overlooking the dominant role of content data in real-world applications. Additionally, the high proportion of non-interacted items exacerbates the sparsity of target behavior data. (2) Current methods jointly model users and items but fail to explicitly distinguish their unique characteristics, leading to an incomplete understanding of diverse item behaviors. To address these issues, we propose Fuzzy Clustering-based Dual-Channel Contrastive Learning(a commonly used algorithm in artificial intelligence) (FCCL) model for multi-behavior recommendation. FCCL first employs a graph convolutional network to generate user and item embeddings independently, leveraging contrastive learning (CL) to capture explicit and implicit features. Subsequently, a dual-channel linear module based on fuzzy clustering is introduced to model both user interest diffusion and item provider influence. In the first layer, a user-level fuzzy clustering CL method is proposed to capture user–item similarities through a fused loss function. The second layer applies item-level hard clustering to characterize item-entity relationships, mitigating sparsity by identifying relevant items, including non-interacted ones. Finally, these tasks are integrated to enhance the quality of user and item embeddings, and a dual-channel optimization mechanism is established to optimize model parameters. Extensive experiments conducted on several public datasets demonstrate that FCCL significantly outperforms existing multi-behavior recommendation models in terms of effectiveness.