Recurrent Coevolutionary Latent Feature Processes for Continuous-Time Recommendation

Abstract

Matching users to the right items at the right time is a fundamental task in recommender systems. As users interact with different items over time, users' and items' feature may drift, evolve and co-evolve over time. Traditional models based on static latent features or discretizing time into epochs can become ineffective for capturing the fine-grained… (More)
DOI: 10.1145/2988450.2988451

Topics

2 Figures and Tables

Cite this paper

@inproceedings{Dai2016RecurrentCL, title={Recurrent Coevolutionary Latent Feature Processes for Continuous-Time Recommendation}, author={Hanjun Dai and Yichen Wang and Rakshit Trivedi and Le Song}, booktitle={DLRS 2016}, year={2016} }