Sequential Recommendation on Temporal Proximities with Contrastive Learning and Self-Attention
This work addresses the problem of enhancing sequential recommender systems for users and platforms by better capturing temporal patterns, though it appears incremental as it builds on existing transformer-based methods with novel adaptations.
The paper tackles the problem of sequential recommendation by addressing underexplored temporal contexts, such as vertical and horizontal temporal proximities, using a model called TemProxRec that combines contrastive learning and self-attention. The result is that TemProxRec consistently outperforms existing models on benchmark datasets, demonstrating improved accuracy in predicting relevant items based on user-item interactions within specific timeframes.
Sequential recommender systems identify user preferences from their past interactions to predict subsequent items optimally. Although traditional deep-learning-based models and modern transformer-based models in previous studies capture unidirectional and bidirectional patterns within user-item interactions, the importance of temporal contexts, such as individual behavioral and societal trend patterns, remains underexplored. Notably, recent models often neglect similarities in users' actions that occur implicitly among users during analogous timeframes-a concept we term vertical temporal proximity. These models primarily adapt the self-attention mechanisms of the transformer to consider the temporal context in individual user actions. Meanwhile, this adaptation still remains limited in considering the horizontal temporal proximity within item interactions, like distinguishing between subsequent item purchases within a week versus a month. To address these gaps, we propose a sequential recommendation model called TemProxRec, which includes contrastive learning and self-attention methods to consider temporal proximities both across and within user-item interactions. The proposed contrastive learning method learns representations of items selected in close temporal periods across different users to be close. Simultaneously, the proposed self-attention mechanism encodes temporal and positional contexts in a user sequence using both absolute and relative embeddings. This way, our TemProxRec accurately predicts the relevant items based on the user-item interactions within a specific timeframe. We validate this work through comprehensive experiments on TemProxRec, consistently outperforming existing models on benchmark datasets as well as showing the significance of considering the vertical and horizontal temporal proximities into sequential recommendation.