Sequential Recommendation with User Memory Networks

TLDR

User preferences evolve over time, yet most recommender systems compress a user’s entire history into a single latent vector, losing item‑ or feature‑level correlations between past behaviors and future interests. This work seeks to represent, store, and manipulate users’ historical records in a more explicit, dynamic, and effective manner. The authors introduce a memory‑augmented neural network that integrates collaborative filtering, using an external memory matrix to store and update user histories and adapting the architecture to item‑ and feature‑level scenarios with tailored read/write operations. On four real‑world datasets, the method outperforms state‑of‑the‑art sequential recommenders such as RNNs and Markov chains and reveals interpretable patterns linking past behaviors to future actions.

Abstract

User preferences are usually dynamic in real-world recommender systems, and a user»s historical behavior records may not be equally important when predicting his/her future interests. Existing recommendation algorithms -- including both shallow and deep approaches -- usually embed a user»s historical records into a single latent vector/representation, which may have lost the per item- or feature-level correlations between a user»s historical records and future interests. In this paper, we aim to express, store, and manipulate users» historical records in a more explicit, dynamic, and effective manner. To do so, we introduce the memory mechanism to recommender systems. Specifically, we design a memory-augmented neural network (MANN) integrated with the insights of collaborative filtering for recommendation. By leveraging the external memory matrix in MANN, we store and update users» historical records explicitly, which enhances the expressiveness of the model. We further adapt our framework to both item- and feature-level versions, and design the corresponding memory reading/writing operations according to the nature of personalized recommendation scenarios. Compared with state-of-the-art methods that consider users» sequential behavior for recommendation, e.g., sequential recommenders with recurrent neural networks (RNN) or Markov chains, our method achieves significantly and consistently better performance on four real-world datasets. Moreover, experimental analyses show that our method is able to extract the intuitive patterns of how users» future actions are affected by previous behaviors.