Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation

被引:2
|
作者
Zhu, Jiajie [1 ]
Wang, Yan [1 ]
Zhu, Feng [2 ]
Sun, Zhu [3 ,4 ]
机构
[1] Macquarie Univ, Macquarie Pk, Australia
[2] Ant Grp, Hangzhou, Peoples R China
[3] ASTAR, Inst High Performance Comp, Singapore, Singapore
[4] ASTAR, Frontier Res Ctr, Singapore, Singapore
关键词
Cross-Domain Recommendation; Data Augmentation; Disentangled Representation Learning;
D O I
10.1145/3604915.3608802
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The conventional single-target Cross-Domain Recommendation (CDR) aims to improve the recommendation performance on a sparser target domain by transferring the knowledge from a source domain that contains relatively richer information. By contrast, in recent years, dual-target CDR has been proposed to improve the recommendation performance on both domains simultaneously. However, to this end, there are two challenges in dual-target CDR: (1) how to generate both relevant and diverse augmented user representations, and (2) how to effectively decouple domain-independent information from domain-specific information, in addition to domain-shared information, to capture comprehensive user preferences. To address the above two challenges, we propose a Disentanglement-based framework with Interpolative Data Augmentation for dual-target Cross-Domain Recommendation, called DIDA-CDR. In DIDA-CDR, we first propose an interpolative data augmentation approach to generating both relevant and diverse augmented user representations to augment sparser domain and explore potential user preferences. We then propose a disentanglement module to effectively decouple domain-specific and domain-independent information to capture comprehensive user preferences. Both steps significantly contribute to capturing more comprehensive user preferences, thereby improving the recommendation performance on each domain. Extensive experiments conducted on five real-world datasets show the significant superiority of DIDA-CDR over the state-of-the-art methods.
引用
收藏
页码:515 / 527
页数:13
相关论文
共 50 条
  • [1] Cross-reconstructed Augmentation for Dual-target Cross-domain Recommendation
    Mao, Qingyang
    Liu, Qi
    Li, Zhi
    Wu, Likang
    Lv, Bing
    Zhang, Zheng
    PROCEEDINGS OF THE 47TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2024, 2024, : 2352 - 2356
  • [2] Dual-Target Cross-Domain Bundle Recommendation
    Zhang, Tao
    Han, Yani
    Dong, Xuewen
    Xu, Yang
    Shen, Yulong
    2021 IEEE INTERNATIONAL CONFERENCE ON SERVICES COMPUTING (SCC 2021), 2021, : 183 - 192
  • [3] DTCDR: A Framework for Dual-Target Cross-Domain Recommendation
    Zhu, Feng
    Chen, Chaochao
    Wang, Yan
    Liu, Guanfeng
    Zheng, Xiaolin
    PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19), 2019, : 1533 - 1542
  • [4] A Graphical and Attentional Framework for Dual-Target Cross-Domain Recommendation
    Zhu, Feng
    Wang, Yan
    Chen, Chaochao
    Liu, Guanfeng
    Zheng, Xiaolin
    PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 3001 - 3008
  • [5] A Contrastive Learning Framework for Dual-Target Cross-Domain Recommendation
    Lu, Jinhu
    Sun, Guohao
    Fang, Xiu
    Yang, Jian
    He, Wei
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 6332 - 6339
  • [6] Temporal dual-target cross-domain recommendation framework for next basket recommendation
    John Kinglsey Arthur
    Conghua Zhou
    Xiang-Jun Shen
    Ronky Wrancis Amber-Doh
    Jeremiah Osei-Kwakye
    Eric Appiah Mantey
    Discover Computing, 27 (1)
  • [7] Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation
    Chen, Gaode
    Zhang, Xinghua
    Su, Yijun
    Lai, Yantong
    Xiang, Ji
    Zhang, Junbo
    Zheng, Yu
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 4, 2023, : 4149 - 4156
  • [8] Identifiability of Cross-Domain Recommendation via Causal Subspace Disentanglement
    Du, Jing
    Ye, Zesheng
    Guo, Bin
    Yu, Zhiwen
    Yao, Lina
    PROCEEDINGS OF THE 47TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, SIGIR 2024, 2024, : 2091 - 2101
  • [9] Entity knowledge transfer-oriented dual-target cross-domain recommendations
    Li, Yakun
    Wu, Qiang
    Hou, Lei
    Li, Juanzi
    EXPERT SYSTEMS WITH APPLICATIONS, 2022, 195
  • [10] Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation
    Choi, Yoonhyuk
    Choi, Jiho
    Ko, Taewook
    Byun, Hyungho
    Kim, Chong-Kwon
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, : 293 - 303