Deep learning and reinforcement learning in recommender systems
COM1 Level 3
MR1, COM1-03-19
Abstract:
Recommender systems are important in people's everyday life. Deep learning has achieved dramatic success in computer vision (CV) and natural language processing (NLP), because of its powerful ability on feature representation. For the recent two years, many researchers and industrial teams propose excellent deep learning models and deploy them on the commercial systems. More recently, reinforcement learning, which achieved remarkable success in various challenging scenarios that require both dynamic interaction and long-run planning such as playing games, has been introduced to model the recommendation process and shows its potential to handle the interactive nature in recommender systems.
In this talk, Ruiming will present some challenges in applying deep learning and reinforcement learning in recommender systems, and elaborate some deep learning and reinforcement learning based recommendation models proposed by the research team in Noah's Ark Lab. Also, he will show some online AB testing results when applying deep learning and reinforcement learning models in commercial recommender system in Huawei.
Biodata:
Ruiming Tang is a senior researcher in recommendation and search project team, Huawei Noah's Ark Lab. He joined Noah's Ark Lab in 2014. His research topics include recommender systems, deep learning, reinforcement learning and etc. He published multiple research works on top-tier conferences and journals, on the topic of recommender systems, such as WWW, IJCAI, TOIS, RecSys, AAAI. Before joining Huawei, Ruiming received his PhD degree in Computer Science from National University of Singapore (NUS) in 2014 and received his Bachelor degree in Computer Science from Northeastern University in China (NEU) in 2009.