Multi-intent Aware Contrastive Learning for Sequential Recommendation

Intent is a significant latent factor influencing user-item interaction sequences. Prevalent sequence recommendation models that utilize contrastive learning predominantly rely on single-intent representations to direct the training process. However, this paradigm oversimplifies real-world recommendation scenarios, attempting to encapsulate the diversity of intents within the single-intent level representation. SR models considering multi-intent information in their framework are more likely to reflect real-life recommendation scenarios accurately. To this end, we propose a Multi-intent Aware Contrastive Learning for Sequential Recommendation (MCLRec). It integrates an intent-aware user representation learning method to enable multi-intent recognition within interaction sequences through the spatial relationships between user and intent representations. We further propose a multi-intent aware contrastive learning strategy to mitigate the impact of pair-wise representations with high similarity. Experimental results on widely used four datasets demonstrate the effectiveness of our method for sequential recommendation.