MARS: Memory Attention-Aware Recommender System
arXiv:1805.07037
Abstract
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.
References in corpus (10)
- BPR: Bayesian Personalized Ranking from Implicit Feedback
- Ask the GRU: Multi-Task Learning for Deep Text Recommendations
- Wide & Deep Learning for Recommender Systems
- Neural Collaborative Filtering
- Neural Factorization Machines for Sparse Predictive Analytics
- Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks
- Joint Deep Modeling of Users and Items Using Reviews for Recommendation
- Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks
- Deep Interest Network for Click-Through Rate Prediction
- Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation
Cited by in corpus (5)
- Deep Learning based Recommender System: A Survey and New Perspectives
- Deep Learning Techniques for Future Intelligent Cross-Media Retrieval
- User Diverse Preference Modeling by Multimodal Attentive Metric Learning
- Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems
- An Introductory Survey on Attention Mechanisms in NLP Problems