Cross-domain Recommendation Without Sharing User-relevant Data

被引:80
作者
Gao, Chen [1 ]
Chen, Xiangning [1 ]
Feng, Fuli [2 ]
Zhao, Kai [1 ]
He, Xiangnan [3 ]
Li, Yong [1 ]
Jin, Depeng [1 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, Beijing Natl Res Ctr Informat Sci & Technol BNRis, Beijing, Peoples R China
[2] Natl Univ Singapore, Sch Comp, Singapore, Singapore
[3] Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei, Anhui, Peoples R China
来源
WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019) | 2019年
基金
新加坡国家研究基金会;
关键词
Cross-domain Recommendation; Privacy Preserving; Deep Learning;
D O I
10.1145/3308558.3313538
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Web systems that provide the same functionality usually share a certain amount of items. This makes it possible to combine data from different websites to improve recommendation quality, known as the cross-domain recommendation task. Despite many research efforts on this task, the main drawback is that they largely assume the data of different systems can be fully shared. Such an assumption is unrealistic different systems are typically operated by different companies, and it may violate business privacy policy to directly share user behavior data since it is highly sensitive. In this work, we consider a more practical scenario to perform cross-domain recommendation. To avoid the leak of user privacy during the data sharing process, we consider sharing only the information of the item side, rather than user behavior data. Specifically, we transfer the item embeddings across domains, making it easier for two companies to reach a consensus (e.g., legal policy) on data sharing since the data to be shared is user-irrelevant and has no explicit semantics. To distill useful signals from transferred item embeddings, we rely on the strong representation power of neural networks and develop a new method named as NATR (short for Neural Attentive Transfer Recommendation). We perform extensive experiments on two real-world datasets, demonstrating that NATR achieves similar or even better performance than traditional cross domain recommendation methods that directly share user-relevant data. Further insights are provided on the efficacy of NATR in using the transferred item embeddings to alleviate the data sparsity issue.
引用
收藏
页码:491 / 502
页数:12
相关论文
共 50 条
  • [31] Cross-domain recommendation via knowledge distillation
    Li, Xiuze
    Huang, Zhenhua
    Wu, Zhengyang
    Wang, Changdong
    Chen, Yunwen
    KNOWLEDGE-BASED SYSTEMS, 2025, 311
  • [32] Privacy Passport: Privacy-Preserving Cross-Domain Data Sharing
    Chen, Xue
    Wang, Cheng
    Yang, Qing
    Teng, Hu
    Jiang, Changjun
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2025, 20 : 636 - 650
  • [33] Domain-Oriented Knowledge Transfer for Cross-Domain Recommendation
    Zhao, Guoshuai
    Zhang, Xiaolong
    Tang, Hao
    Shen, Jialie
    Qian, Xueming
    IEEE TRANSACTIONS ON MULTIMEDIA, 2024, 26 : 9539 - 9550
  • [34] Domain-Invariant Task Optimization for Cross-domain Recommendation
    Liu, Dou
    Hao, Qingbo
    Xiao, Yingyuan
    Zheng, Wenguang
    Wang, Jinsong
    NEURAL INFORMATION PROCESSING, ICONIP 2023, PT III, 2024, 14449 : 488 - 499
  • [35] Privacy-Preserving Cross-Domain Sequential Recommendation
    Lin, Zhaohao
    Pan, Weike
    Ming, Zhong
    23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING, ICDM 2023, 2023, : 1139 - 1144
  • [36] Adaptive Adversarial Contrastive Learning for Cross-Domain Recommendation
    Hsu, Chi-Wei
    Chen, Chiao-Ting
    Huang, Szu-Hao
    ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA, 2024, 18 (03)
  • [37] Cross-Domain Recommendation via Preference Propagation GraphNet
    Zhao, Cheng
    Li, Chenliang
    Fu, Cong
    PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM '19), 2019, : 2165 - 2168
  • [38] Cross-Domain Recommendation for Mapping Sentiment Review Pattern
    Xu, Yang
    Peng, Zhaohui
    Hu, Yupeng
    Hong, Xiaoguang
    Fu, Wenjing
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT (KSEM 2018), PT I, 2018, 11061 : 324 - 336
  • [39] A deep selective learning network for cross-domain recommendation
    Liu, Huiting
    Liu, Qian
    Li, Peipei
    Zhao, Peng
    Wu, Xindong
    APPLIED SOFT COMPUTING, 2022, 125
  • [40] Deep Graph Mutual Learning for Cross-domain Recommendation
    Wang, Yifan
    Li, Yongkang
    Li, Shuai
    Song, Weiping
    Fan, Jiangke
    Gao, Shan
    Ma, Ling
    Cheng, Bing
    Cai, Xunliang
    Wang, Sheng
    Zhang, Ming
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT II, 2022, : 298 - 305