| Autor: |
ZIHUA SI1 zihua_si@ruc.edu.cn, ZHONGXIANG SUN1 sunzhongxiang@ruc.edu.cn, XIAO ZHANG1 zhangx89@ruc.edu.cn, JUN XU1 junxu@ruc.edu.cn, YANG SONG2 yangsong@kuaishou.com, XIAOXUE ZANG2 zangxiaoxue@kuaishou.com, JI-RONG WEN1 jrwen@ruc.edu.cn |
| Zdroj: |
ACM Transactions on Information Systems. Oct2023, Vol. 41 Issue 4, p1-31. 31p. |
| Abstrakt: |
The article focuses on enhancing recommender systems by addressing the challenges of mixed causal and non-causal associations in user feedback. Topics include the proposal of a model-agnostic causal learning framework called IV4Rec that uses search queries as instrumental variables, the decomposition of embedding vectors into causal and non-causal parts, and the improvement of recommendation system performance through this approach. |
| Databáze: |
Library, Information Science & Technology Abstracts |
| Externí odkaz: |
|
