Deep Graph Mutual Learning for Cross-domain Recommendation

被引:3
|
作者
Wang, Yifan [1 ]
Li, Yongkang [1 ]
Li, Shuai [1 ]
Song, Weiping [1 ]
Fan, Jiangke [2 ]
Gao, Shan [2 ]
Ma, Ling [2 ]
Cheng, Bing [2 ]
Cai, Xunliang [2 ]
Wang, Sheng [3 ]
Zhang, Ming [1 ]
机构
[1] Peking Univ, Sch Comp Sci, Beijing, Peoples R China
[2] Meituan, Beijing, Peoples R China
[3] Univ Washington, Paul G Allen Sch Comp Sci, Seattle, WA USA
基金
中国国家自然科学基金;
关键词
Cross-domain recommendation; Collaborative filtering; Graph neural networks; Mutual learning;
D O I
10.1007/978-3-031-00126-0_22
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Cross-domain recommender systems have been increasingly important for helping users find satisfying items from different domains. However, existing approaches mostly share/map user features among different domains to transfer the knowledge. In fact, user-item interactions can be formulated as a bipartite graph and knowledge transferring through the graph is a more explicit way. Meanwhile, these approaches mostly focus on capturing users' common interests, overlooking domain-specific preferences. In this paper, we propose a novel Deep Graph Mutual Learning framework (DGML) for cross-domain recommendation. In particular, we first separately construct domain-shared and domain-specific interaction graphs, and develop a parallel graph neural network to extract user preference in corresponding graph. Then the mutual learning procedure uses extracted preferences to form a more comprehensive user preference. Our extensive experiments on two real-world datasets demonstrate significant improvements over state-of-the-art approaches.
引用
收藏
页码:298 / 305
页数:8
相关论文
共 50 条
  • [1] A deep selective learning network for cross-domain recommendation
    Liu, Huiting
    Liu, Qian
    Li, Peipei
    Zhao, Peng
    Wu, Xindong
    [J]. APPLIED SOFT COMPUTING, 2022, 125
  • [2] Deep shared learning and attentive domain mapping for cross-domain recommendation
    Gheewala, Shivangi
    Xu, Shuxiang
    Yeom, Soonja
    [J]. USER MODELING AND USER-ADAPTED INTERACTION, 2024,
  • [3] Deep Cross-Domain Fashion Recommendation
    Jaradat, Shatha
    [J]. PROCEEDINGS OF THE ELEVENTH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS'17), 2017, : 407 - 410
  • [4] Graph Disentangled Contrastive Learning with Personalized Transfer for Cross-Domain Recommendation
    Liu, Jing
    Sun, Lele
    Nie, Weizhi
    Jing, Peiguang
    Su, Yuting
    [J]. THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 8, 2024, : 8769 - 8777
  • [5] Heterogeneous Graph Embedding for Cross-Domain Recommendation Through Adversarial Learning
    Li, Jin
    Peng, Zhaohui
    Wang, Senzhang
    Xu, Xiaokang
    Yu, Philip S.
    Hao, Zhenyun
    [J]. DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2020), PT III, 2020, 12114 : 507 - 522
  • [6] Heterogeneous graph contrastive learning for cold start cross-domain recommendation
    Xie, Yuanzhen
    Yu, Chenyun
    Jin, Xinzhou
    Cheng, Lei
    Hu, Bo
    Li, Zang
    [J]. KNOWLEDGE-BASED SYSTEMS, 2024, 299
  • [7] Privacy-preserving Cross-domain Recommendation with Federated Graph Learning
    Tian, Changxin
    Xie, Yuexiang
    Chen, Xu
    Li, Yaliang
    Zhao, Xin
    [J]. ACM TRANSACTIONS ON INFORMATION SYSTEMS, 2024, 42 (05)
  • [8] Latent mutual feature extraction for cross-domain recommendation
    Park, Hoon
    Jung, Jason J.
    [J]. KNOWLEDGE AND INFORMATION SYSTEMS, 2024, 66 (06) : 3337 - 3354
  • [9] Heterogeneous Graph Representation Learning for multi-target Cross-Domain Recommendation
    Mukande, Tendai
    [J]. PROCEEDINGS OF THE 16TH ACM CONFERENCE ON RECOMMENDER SYSTEMS, RECSYS 2022, 2022, : 730 - 734
  • [10] A Cross-Domain Recommendation Algorithm Based On Graph Optimization
    Fan, Zheng
    Wang, Ying-Li
    Ma, Qi-Tao
    Du, Hai-Xia
    Ma, Hong-Bin
    [J]. Journal of Network Intelligence, 2023, 8 (03): : 856 - 868