MARS: Memory Attention-Aware Recommender System
This addresses the limitation of fixed user representations in recommendation systems for users and platforms, offering an incremental improvement with interpretable results.
The paper tackles the problem of modeling users' diverse interests in recommendation systems by proposing MARS, which uses a memory component and attentional mechanism to learn adaptive user representations, outperforming seven state-of-the-art methods on three datasets with improved recall and mean average precision.
In this paper, we study the problem of modeling users' diverse interests. Previous methods usually learn a fixed user representation, which has a limited ability to represent distinct interests of a user. In order to model users' various interests, we propose a Memory Attention-aware Recommender System (MARS). MARS utilizes a memory component and a novel attentional mechanism to learn deep \textit{adaptive user representations}. Trained in an end-to-end fashion, MARS adaptively summarizes users' interests. In the experiments, MARS outperforms seven state-of-the-art methods on three real-world datasets in terms of recall and mean average precision. We also demonstrate that MARS has a great interpretability to explain its recommendation results, which is important in many recommendation scenarios.