Feature Decomposition for Reducing Negative Transfer: A Novel Multi-Task Learning Method for Recommender System (Student Abstract)
Jie Zhou, Qian Yu, Chuan Luo, Jing Zhang
Abstract
We propose a novel multi-task learning method termed Feature Decomposition Network (FDN). The key idea of the proposed FDN is to reduce the phenomenon of feature redundancy by explicitly decomposing features into task-specific features and task-shared features with carefully designed constraints. Experimental results show that our proposed FDN can outperform the state-of-the-art (SOTA) methods by a noticeable margin on Ali-CCP.
Topics & Concepts
Computer scienceRedundancy (engineering)Margin (machine learning)Task (project management)Feature (linguistics)Artificial intelligenceDecompositionKey (lock)Recommender systemTransfer of learningMachine learningPattern recognition (psychology)EngineeringLinguisticsEcologyPhilosophyComputer securityBiologyOperating systemSystems engineeringText and Document Classification TechnologiesRecommender Systems and TechniquesMachine Learning and Data Classification