Attention Mixtures for Time-Aware Sequential Recommendation
This work addresses the problem of improving recommendation accuracy for users by incorporating temporal context, though it appears incremental as it builds on existing Transformer methods.
The paper tackles the problem of sequential recommendation by addressing the complex dependencies between user preferences and temporal context, introducing MOJITO, an improved Transformer that uses Gaussian mixtures of attention-based representations to predict next items, and empirically shows it outperforms existing Transformers on several real-world datasets.
Transformers emerged as powerful methods for sequential recommendation. However, existing architectures often overlook the complex dependencies between user preferences and the temporal context. In this short paper, we introduce MOJITO, an improved Transformer sequential recommender system that addresses this limitation. MOJITO leverages Gaussian mixtures of attention-based temporal context and item embedding representations for sequential modeling. Such an approach permits to accurately predict which items should be recommended next to users depending on past actions and the temporal context. We demonstrate the relevance of our approach, by empirically outperforming existing Transformers for sequential recommendation on several real-world datasets.