Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation

被引:8
|
作者
Choi, Yoonhyuk [1 ]
Choi, Jiho [1 ]
Ko, Taewook [1 ]
Byun, Hyungho [1 ]
Kim, Chong-Kwon [2 ]
机构
[1] Seoul Natl Univ, Seoul, South Korea
[2] Korea Inst Energy Technol, Naju, South Korea
基金
新加坡国家研究基金会;
关键词
Cross-Domain Recommendation; Disentangled Representation Learning; Domain Adaptation; Textual Analysis; ADVERSARIAL;
D O I
10.1145/3511808.3557434
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A cross-domain recommendation has shown promising results in solving data-sparsity and cold-start problems. Despite such progress, existing methods focus on domain-shareable information (overlapped users or same contexts) for a knowledge transfer, and they fail to generalize well without such requirements. To deal with these problems, we suggest utilizing review texts that are general to most e-commerce systems. Our model (named SER) uses three text analysis modules, guided by a single domain discriminator for disentangled representation learning. Here, we suggest a novel optimization strategy that can enhance the quality of domain disentanglement, and also debilitates detrimental information of a source domain. Also, we extend the encoding network from a single to multiple domains, which has proven to be powerful for review-based recommender systems. Extensive experiments and ablation studies demonstrate that our method is efficient, robust, and scalable compared to the state-of-the-art single and cross-domain recommendation methods.
引用
收藏
页码:293 / 303
页数:11
相关论文
共 50 条
  • [1] Review-Based Cross-Domain Recommendation Through Joint Tensor Factorization
    Song, Tianhang
    Peng, Zhaohui
    Wang, Senzhang
    Fu, Wenjing
    Hong, Xiaoguang
    Yu, Philip S.
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2017), PT I, 2017, 10177 : 525 - 540
  • [2] Identifiability of Cross-Domain Recommendation via Causal Subspace Disentanglement
    Du, Jing
    Ye, Zesheng
    Guo, Bin
    Yu, Zhiwen
    Yao, Lina
    [J]. PROCEEDINGS OF THE 47TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2024, 2024, : 2091 - 2101
  • [3] Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation
    Zhu, Jiajie
    Wang, Yan
    Zhu, Feng
    Sun, Zhu
    [J]. PROCEEDINGS OF THE 17TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, RECSYS 2023, 2023, : 515 - 527
  • [4] Cross-domain collaborative recommendation without overlapping entities based on domain adaptation
    Hongwei Zhang
    Xiangwei Kong
    Yujia Zhang
    [J]. Multimedia Systems, 2022, 28 : 1621 - 1637
  • [5] Cross-domain collaborative recommendation without overlapping entities based on domain adaptation
    Zhang, Hongwei
    Kong, Xiangwei
    Zhang, Yujia
    [J]. MULTIMEDIA SYSTEMS, 2022, 28 (05) : 1621 - 1637
  • [6] IDC-CDR: Cross-domain Recommendation based on Intent Disentanglement and Contrast Learning
    Xu, Jing
    Gan, Mingxin
    Zhang, Hang
    Zhang, Shuhao
    [J]. INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (06)
  • [7] C 2DR: Robust Cross-Domain Recommendation based on Causal Disentanglement
    Kong Menglin
    Wang, Jia
    Pan, Yushan
    Zhang, Haiyang
    Hou, Muzhou
    [J]. PROCEEDINGS OF THE 17TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, WSDM 2024, 2024, : 341 - 349
  • [8] Cross-domain recommendation without shared users or items by sharing latent vector distributions
    Iwata, Tomoharu
    Takeuchi, Koh
    [J]. ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 38, 2015, 38 : 379 - 387
  • [9] DCDIR: A Deep Cross-Domain Recommendation System for Cold Start Users in Insurance Domain
    Bi, Ye
    Song, Liqiang
    Yao, Mengqiu
    Wu, Zhenyu
    Wang, Jianming
    Xiao, Jing
    [J]. PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20), 2020, : 1661 - 1664
  • [10] Debiasing Learning based Cross-domain Recommendation
    Li, Siqing
    Yao, Liuyi
    Mu, Shanlei
    Zhao, Wayne Xin
    Li, Yaliang
    Guo, Tonglei
    Ding, Bolin
    Wen, Ji-Rong
    [J]. KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 3190 - 3199