中国邮电高校学报(英文版) ›› 2020, Vol. 27 ›› Issue (5): 13-22.doi: 10.19682/j.cnki.1005-8885.2020.0025

• Artificial Intelligence • 上一篇    下一篇

Fast TMRM: efficient multi-task recommendation model

朱帆; 杨娟   

  1. 北京邮电大学
  • 收稿日期:2020-01-19 修回日期:2020-04-11 出版日期:2020-10-22 发布日期:2020-10-23
  • 通讯作者: 朱帆 E-mail:13269476570@163.com

Fast TMRM: efficient multi-task recommendation model

Zhu Fan, Yang Juan   

  1. School of Computer Science and Technology, Beijing University of Posts and Telecommunications
  • Received:2020-01-19 Revised:2020-04-11 Online:2020-10-22 Published:2020-10-23
  • Contact: Fan ZHU E-mail:13269476570@163.com

摘要: An improved multi-task learning recommendation algorithm—fast two-stage multi-task recommendation model boosted feature selection (Fast TMRM) is proposed based on auto-encoders in this paper. Compared to previous work, Fast TMRM improves the convergence speed and accuracy of training. In addition, Fast TMRM builds on previous work to introduce the auto-encoder to encode the important feature combination vector. That is how it can be used for the training of multi-task learning, which helps to improve the training efficiency of the model by nearly 67%. Finally, the nearest neighbor search is used to restore important feature expression.

关键词: recommendation algorithm, feature combination, auto-encoder

Abstract: An improved multi-task learning recommendation algorithm—fast two-stage multi-task recommendation model boosted feature selection (Fast TMRM) is proposed based on auto-encoders in this paper. Compared to previous work, Fast TMRM improves the convergence speed and accuracy of training. In addition, Fast TMRM builds on previous work to introduce the auto-encoder to encode the important feature combination vector. That is how it can be used for the training of multi-task learning, which helps to improve the training efficiency of the model by nearly 67%. Finally, the nearest neighbor search is used to restore important feature expression.

Key words: recommendation algorithm, feature combination, auto-encoder