Causal Embeddings for Recommendation

被引:170
|
作者
Bonner, Stephen [1 ,2 ]
Vasile, Flavian [1 ]
机构
[1] Criteo AI Labs, Paris, France
[2] Univ Durham, Dept Comp Sci, Durham, England
关键词
Recommender Systems; Causality; Embeddings; Neural Networks; Counterfactual Inference;
D O I
10.1145/3240323.3240360
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many current applications use recommendations in order to modify the natural user behavior, such as to increase the number of sales or the time spent on a website. This results in a gap between the final recommendation objective and the classical setup where recommendation candidates are evaluated by their coherence with past user behavior, by predicting either the missing entries in the user-item matrix, or the most likely next event. To bridge this gap, we optimize a recommendation policy for the task of increasing the desired outcome versus the organic user behavior. We show this is equivalent to learning to predict recommendation outcomes under a fully random recommendation policy. To this end, we propose a new domain adaptation algorithm that learns from logged data containing outcomes from a biased recommendation policy and predicts recommendation outcomes according to random exposure. We compare our method against state-of-the-art factorization methods, in addition to new approaches of causal recommendation and show significant improvements.
引用
收藏
页码:104 / 112
页数:9
相关论文
共 50 条
  • [21] Query Recommendation Using Topic Modeling and Word Embeddings
    Duan, Jianyong
    Song, Yadi
    Zhang, Yongmei
    Wu, Mingli
    Wang, Hao
    2018 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION (AIPR 2018), 2018, : 86 - 92
  • [22] Recommendation of Points-of-Interest using Graph Embeddings
    Christoforidis, Giannis
    Kefalas, Pavlos
    Papadopoulos, Apostolos N.
    Manolopoulos, Yannis
    2018 IEEE 5TH INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA), 2018, : 31 - 40
  • [23] BRUCE: Bundle Recommendation Using Contextualized item Embeddings
    Brosh, Tzoof Avny
    Livne, Amit
    Shalom, Oren Sar
    Shapira, Bracha
    Last, Mark
    PROCEEDINGS OF THE 16TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, RECSYS 2022, 2022, : 237 - 245
  • [24] Regularizing Matrix Factorization with User and Item Embeddings for Recommendation
    Thanh Tran
    Lee, Kyumin
    Liao, Yiming
    Lee, Dongwon
    CIKM'18: PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2018, : 687 - 696
  • [25] Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
    Ai, Qingyao
    Azizi, Vahid
    Chen, Xu
    Zhang, Yongfeng
    ALGORITHMS, 2018, 11 (09)
  • [26] Distilling Structured Knowledge into Embeddings for Explainable and Accurate Recommendation
    Zhang, Yuan
    Xu, Xiaoran
    Zhou, Hanning
    Zhang, Yan
    PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM '20), 2020, : 735 - 743
  • [27] Monitoring the Evolution of Behavioural Embeddings in Social Media Recommendation
    Saket, Srijan
    Jeunen, Olivier
    Kalim, Md. Danish
    PROCEEDINGS OF THE 47TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2024, 2024, : 2935 - 2939
  • [28] A Counterfactual Neural Causal Model for Interactive Recommendation
    Liu, Jialin
    He, Zeyu
    Zhou, Peng
    Su, Xinyan
    Li, Jun
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 1609 - 1614
  • [29] A Novel Causal Discovery Model for Recommendation System
    Sun, Guohao
    Hua, Huirong
    Lu, Jinhu
    Fang, Xiu
    WEB AND BIG DATA, PT IV, APWEB-WAIM 2023, 2024, 14334 : 261 - 276
  • [30] STEM: Unleashing the Power of Embeddings for Multi-Task Recommendation
    Su, Liangcai
    Pan, Junwei
    Wang, Ximei
    Xiao, Xi
    Quan, Shijie
    Chen, Xihua
    Jiang, Jie
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 8, 2024, : 9002 - 9010