Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation

  title={Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation},
  author={Chao Chen and Dongsheng Li and Junchi Yan and Xiaokang Yang},
  journal={IEEE Transactions on Knowledge and Data Engineering},
Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time. Many existing recommendation algorithms – including both shallow and deep ones – often model such dynamics independently, i.e., user static and dynamic preferences are not modeled under the same latent space, which makes it difficult to fuse them for recommendation. This paper considers the problem of embedding a user's sequential behavior into the latent… 

Figures and Tables from this paper

Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation

A novel attention network, named self-modulating attention , is proposed, that models the complex and non-linearly evolving dynamic user preferences and empirically demonstrates the effectiveness of the method on top-N sequential recommendation tasks, and results on three large-scale real-world datasets show that the model can achieve state-of-the-art performance.

SelfCF: A Simple Framework for Self-supervised Collaborative Filtering

This paper proposes a self-supervised collaborative filtering framework (SelfCF), that is specially designed for recommender scenario with implicit feedback, and enables learning informative representations of users and items without negative samples, and is agnostic to the encapsulated backbones.

Parallel Split-Join Networks for Shared Account Cross-Domain Sequential Recommendations

This work studies shared account cross-domain sequential recommendation and proposes a parallel split-join Network (Parallel Split-Join Network (PSJNet), a parallel modeling network to address the two challenges above.

Incremental Graph Convolutional Network for Collaborative Filtering

Experimental studies on real-world datasets show that IGCN can outperform state-of-the-art CF algorithms in sequential recommendation tasks, and ensures good initial states and fast model adaptation.

Scalable and Explainable 1-Bit Matrix Completion via Graph Signal Learning

The spectral graph matrix completion (SGMC) method is proposed, which can recover the underlying matrix in distributed systems by filtering the noisy data in the graph frequency domain by developing polynomial and sparse frequency filters to remedy the accuracy loss caused by the approximations.



Sequential Recommendation with User Memory Networks

A memory-augmented neural network (MANN) integrated with the insights of collaborative filtering for recommendation is designed, which store and update users» historical records explicitly, which enhances the expressiveness of the model.

Sequential Recommender System based on Hierarchical Attention Networks

A novel two-layer hierarchical attention network is proposed, which takes the above properties into account, to recommend the next item user might be interested and demonstrates the superiority of the method compared with other state-of-the-art ones.

Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation

Fossil is proposed, a similarity-based method that outperforms alternative algorithms, especially on sparse datasets, and qualitatively that it captures personalized dynamics and is able to make meaningful recommendations.

Learning Hierarchical Representation Model for NextBasket Recommendation

This paper introduces a novel recommendation approach, namely hierarchical representation model (HRM), which can well capture both sequential behavior and users' general taste by involving transaction and user representations in prediction.

A Dynamic Recurrent Model for Next Basket Recommendation

This work proposes a novel model, Dynamic REcurrent bAsket Model (DREAM), based on Recurrent Neural Network (RNN), which not only learns a dynamic representation of a user but also captures global sequential features among baskets.

Recurrent Recommender Networks

Recurrent Recommender Networks (RRN) are proposed that are able to predict future behavioral trajectories by endowing both users and movies with a Long Short-Term Memory (LSTM) autoregressive model that captures dynamics, in addition to a more traditional low-rank factorization.

Adapting Recommendations to Contextual Changes Using Hierarchical Hidden Markov Models

This paper introduces a hierarchical hidden Markov model for capturing changes in user's preferences using a user's feedback sequence on items and the current context of the user as a hidden variable in this model.

Factorizing personalized Markov chains for next-basket recommendation

This paper introduces an adaption of the Bayesian Personalized Ranking (BPR) framework for sequential basket data and shows that the FPMC model outperforms both the common matrix factorization and the unpersonalized MC model both learned with and without factorization.

Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks

This paper proposes a novel knowledge enhanced sequential recommender that integrates the RNN-based networks with Key-Value Memory Network (KV-MN) and incorporates knowledge base information to enhance the semantic representation of KV- MN.

Modeling relationships at multiple scales to improve accuracy of large recommender systems

Both the local and the regional approaches, and in particular their combination through a unifying model, compare favorably with other approaches and deliver substantially better results than the commercial Netflix Cinematch recommender system on a large publicly available data set.