Feature Decomposition for Reducing Negative Transfer: A Novel Multi-Task Learning Method for Recommender System (Student Abstract)

Authors

  • Jie Zhou School of Software, Beihang University, China
  • Qian Yu School of Software, Beihang University, China
  • Chuan Luo School of Software, Beihang University, China
  • Jing Zhang School of Software, Beihang University, China

DOI:

https://doi.org/10.1609/aaai.v37i13.27055

Keywords:

Multi-task Learning, Negative Transfer, Recommender System

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.
AAAI-23 Proceedings Cover

Downloads

Published

2023-09-06

How to Cite

Zhou, J., Yu, Q., Luo, C., & Zhang, J. (2023). Feature Decomposition for Reducing Negative Transfer: A Novel Multi-Task Learning Method for Recommender System (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 16390-16391. https://doi.org/10.1609/aaai.v37i13.27055

Issue

Vol. 37 No. 13: AAAI-23 Special Programs, IAAI-23, EAAI-23, Student Papers and Demonstrations

Section

AAAI Student Abstract and Poster Program