A0924
Title: Continuous-time recommender system for implicit feedback
Authors: Xiwei Tang - University of Virginia (United States) [presenting]
Abstract: Large volumes of temporal event data are drawing increasing attention in various applications, such as analyzing social media data, healthcare records, online consumption, and product recommendation. Traditional models based on static latent features or discretized time epochs for the recommender system usually fail to capture the essential temporal dynamics in user-item interactions. A novel evolutionary recommender system is proposed by leveraging the temporal mechanism on the continuous-time user-item interactive events. The proposed approach can effectively capture the long- and short-term preferences from the sequential historical data with informative dynamic feature embeddings. An efficient algorithm for learning the model parameters with outstanding scalability and computational effectiveness is developed. Using both synthetic and real-world datasets, the outperformance of the proposed model in learning sequential user behaviours and achieving better predictive power in recommendation is shown.
