Multitask Mixture of Sequential Experts for User Activity Streams
Zhen Qin, Yicheng Cheng, Zhe Zhao, Zhe Chen, Donald Metzler, Jingzheng Qin
Abstract
It is often desirable to model multiple objectives in real-world web applications, such as user satisfaction and user engagement in recommender systems. Multi-task learning has become the standard approach for such applications recently.
Topics & Concepts
Computer scienceRecommender systemTask (project management)User satisfactionHuman–computer interactionWorld Wide WebMultimediaManagementEconomicsRecommender Systems and TechniquesData Stream Mining TechniquesAdvanced Bandit Algorithms Research