Contrastive Learning Method for Sequential Recommendation based on Multi-Intention Disentanglement
This work addresses the problem of improving personalized recommendations for users in systems with large volumes and rich behavioral data, though it appears incremental as it builds on existing contrastive learning and disentanglement techniques.
The paper tackles the challenge of understanding and disentangling users' multiple dynamic intentions in sequential recommendation by proposing MIDCL, a contrastive learning method based on multi-intention disentanglement using Variational Auto-Encoder, which shows significant superiority over most baseline methods and provides more interpretable predictions.
Sequential recommendation is one of the important branches of recommender system, aiming to achieve personalized recommended items for the future through the analysis and prediction of users' ordered historical interactive behaviors. However, along with the growth of the user volume and the increasingly rich behavioral information, how to understand and disentangle the user's interactive multi-intention effectively also poses challenges to behavior prediction and sequential recommendation. In light of these challenges, we propose a Contrastive Learning sequential recommendation method based on Multi-Intention Disentanglement (MIDCL). In our work, intentions are recognized as dynamic and diverse, and user behaviors are often driven by current multi-intentions, which means that the model needs to not only mine the most relevant implicit intention for each user, but also impair the influence from irrelevant intentions. Therefore, we choose Variational Auto-Encoder (VAE) to realize the disentanglement of users' multi-intentions. We propose two types of contrastive learning paradigms for finding the most relevant user's interactive intention, and maximizing the mutual information of positive sample pairs, respectively. Experimental results show that MIDCL not only has significant superiority over most existing baseline methods, but also brings a more interpretable case to the research about intention-based prediction and recommendation.