Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations

被引:26
|
作者
Li, Pan [1 ]
Tuzhilin, Alexander [1 ]
机构
[1] NYU, Stern Sch Business, Dept Technol Operat & Stat, New York, NY 10012 USA
基金
澳大利亚研究理事会;
关键词
Cross domain recommendation; dual learning; metric learning; orthogonal mapping; ALGORITHMS;
D O I
10.1109/TKDE.2021.3074395
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Cross domain recommender systems have been increasingly valuable for helping consumers identify useful items in different applications. However, existing cross-domain models typically require large number of overlap users, which can be difficult to obtain in some applications. In addition, they did not consider the duality structure of cross-domain recommendation tasks, thus failing to take into account bidirectional latent relations between users and items and achieve optimal recommendation performance. To address these issues, in this paper we propose a novel cross-domain recommendation model based on dual learning that transfers information between two related domains in an iterative manner until the learning process stabilizes. We develop a novel latent orthogonal mapping to extract user preferences over multiple domains while preserving relations between users across different latent spaces. Furthermore, we combine the dual learning method with the metric learning approach, which allows us to significantly reduce the required common user overlap across the two domains and leads to even better cross-domain recommendation performance. We test the proposed model on two large-scale industrial datasets and six domain pairs, demonstrating that it consistently and significantly outperforms all the state-of-the-art baselines. We also show that the proposed model works well with very few overlap users to obtain satisfying recommendation performance comparable to the state-of-the-art baselines that use many overlap users.
引用
收藏
页码:321 / 334
页数:14
相关论文
共 50 条
  • [41] CDMA: CROSS-DOMAIN DISTANCE METRIC ADAPTATION FOR SPEAKER VERIFICATION
    Li, Jianchen
    Han, Jiqing
    Song, Hongwei
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 7197 - 7201
  • [42] Learning to Adapt Across Dual Discrepancy for Cross-Domain Person Re-Identification
    Luo, Chuanchen
    Song, Chunfeng
    Zhang, Zhaoxiang
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (02) : 1963 - 1980
  • [43] Meta-collaborative comparison for effective cross-domain few-shot learning
    Zhou, Fei
    Wang, Peng
    Zhang, Lei
    Wei, Wei
    Zhang, Yanning
    PATTERN RECOGNITION, 2024, 156
  • [44] DUAL GRAPH CROSS-DOMAIN FEW-SHOT LEARNING FOR HYPERSPECTRAL IMAGE CLASSIFICATION
    Zhang, Yuxiang
    Li, Wei
    Zhang, Mengmeng
    Tao, Ran
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 3573 - 3577
  • [45] Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
    Li, Pan
    Jiang, Zhichao
    Que, Maofei
    Hu, Yao
    Tuzhili, Alexander
    KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 3172 - 3180
  • [46] Representation Learning for Imbalanced Cross-Domain Classification
    Cheng, Lu
    Guo, Ruocheng
    Candan, K. Selcuk
    Liu, Huan
    PROCEEDINGS OF THE 2020 SIAM INTERNATIONAL CONFERENCE ON DATA MINING (SDM), 2020, : 478 - 486
  • [47] Unsupervised Cross-Domain Word Representation Learning
    Bollegala, Danushka
    Maehara, Takanori
    Kawarabayashi, Ken-Ichi
    PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, 2015, : 730 - 740
  • [48] Triple Sequence Learning for Cross-domain Recommendation
    Ma, Haokai
    Xie, Ruobing
    Meng, Lei
    Chen, Xin
    Zhang, Xu
    Lin, Leyu
    Zhou, Jie
    ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2024, 42 (04)
  • [49] Cross-domain Recommendations without Overlapping Data: Myth or Reality?
    Cremonesi, Paolo
    Quadrana, Massimo
    PROCEEDINGS OF THE 8TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'14), 2014, : 297 - 300
  • [50] Cross-domain continual learning via CLAMP
    Weng, Weiwei
    Pratama, Mahardhika
    Zhang, Jie
    Chen, Chen
    Yie, Edward Yapp Kien
    Savitha, Ramasamy
    INFORMATION SCIENCES, 2024, 676