FedCORE: Federated Learning for Cross-Organization Recommendation Ecosystem

被引:0
作者
Li, Zhitao [1 ]
Wu, Xueyang [2 ]
Pan, Weike [1 ]
Ding, Youlong [1 ]
Wu, Zeheng [3 ]
Tan, Shengqi [3 ]
Xu, Qian [2 ]
Yang, Qiang [2 ]
Ming, Zhong [4 ,5 ]
机构
[1] Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Peoples R China
[2] Hong Kong Univ Sci & Technol, Dept Comp Sci & Engn, Clear Water Bay, Hong Kong, Peoples R China
[3] WeBank, Shenzhen 518063, Peoples R China
[4] Shenzhen Univ, Shenzhen 518060, Peoples R China
[5] Shenzhen Technol Univ, Shenzhen 518060, Peoples R China
基金
中国国家自然科学基金;
关键词
Cross-Organization recommendation; federated learning;
D O I
10.1109/TKDE.2024.3363505
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A recommendation system is of vital importance in delivering personalization services, which often brings continuous dual improvement in user experience and organization revenue. However, the data of one single organization may not be enough to build an accurate recommendation model for inactive or new cold-start users. Moreover, due to the recent regulatory restrictions on user privacy and data security, as well as the commercial conflicts, the raw data in different organizations can not be merged to alleviate the scarcity issue in training a model. In order to learn users' preferences from such cross-silo data of different organizations and then provide recommendations to the cold-start users, we propose a novel federated learning framework, i.e., federated cross-organization recommendation ecosystem (FedCORE). Specifically, we first focus on the ecosystem problem of cross-organization federated recommendation, including cooperation patterns and privacy protection. For the former, we propose a privacy-aware collaborative training and inference algorithm. For the latter, we define four levels of privacy leakage and propose some methods for protecting the privacy. We then conduct extensive experiments on three real-world datasets and two seminal recommendation models to study the impact of cooperation in our proposed ecosystem and the effectiveness of privacy protection.
引用
收藏
页码:3817 / 3831
页数:15
相关论文
共 50 条
[41]   Robust Privacy-Preserving Recommendation Systems Driven by Multimodal Federated Learning [J].
Feng, Chenyuan ;
Feng, Daquan ;
Huang, Guanxin ;
Liu, Zuozhu ;
Wang, Zhenzhong ;
Xia, Xiang-Gen .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2025, 36 (05) :8896-8910
[42]   Consumer Product Recommendation System Using Adapted PSO With Federated Learning Method [J].
Devarajan, Ganesh Gopal ;
Nagarajan, Senthil Murugan ;
Daniel, A. ;
Vignesh, T. ;
Kaluri, Rajesh .
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2024, 70 (01) :2708-2715
[43]   SCFL: Spatio-temporal consistency federated learning for next POI recommendation [J].
Zhong, Lin ;
Zeng, Jun ;
Wang, Ziwei ;
Zhou, Wei ;
Wen, Junhao .
INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (06)
[44]   Federated learning for supervised cross-modal retrieval [J].
Li, Ang ;
Li, Yawen ;
Shao, Yingxia .
WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2024, 27 (04)
[45]   Cross-Silo Federated Learning-to-Rank [J].
Shi D.-Y. ;
Wang Y.-S. ;
Zheng P.-F. ;
Tong Y.-X. .
Ruan Jian Xue Bao/Journal of Software, 2021, 32 (03) :669-688
[46]   FedX: Unsupervised Federated Learning with Cross Knowledge Distillation [J].
Han, Sungwon ;
Park, Sungwon ;
Wu, Fangzhao ;
Kim, Sundong ;
Wu, Chuhan ;
Xie, Xing ;
Cha, Meeyoung .
COMPUTER VISION - ECCV 2022, PT XXX, 2022, 13690 :691-707
[47]   FairFed: Cross-Device Fair Federated Learning [J].
Rehman, Muhammad Habib Ur ;
Dirir, Ahmed Mukhtar ;
Salah, Khaled ;
Svetinovic, Davor .
2020 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR): TRUSTED COMPUTING, PRIVACY, AND SECURING MULTIMEDIA, 2020,
[48]   Heterogeneity-aware Cross-school Electives Recommendation: a Hybrid Federated Approach [J].
Ju, Chengyi ;
Cao, Jiannong ;
Yang, Yu ;
Yang, Zhen-Qun ;
Lee, Ho Man .
2023 23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS, ICDMW 2023, 2023, :1500-1508
[49]   Federated cross-domain recommendation system based on bias eliminator and personalized extractor [J].
Di, Yicheng ;
Shi, Hongjian ;
Wang, Qi ;
Jia, Shunyuan ;
Bao, Jiayu ;
Liu, Yuan .
KNOWLEDGE AND INFORMATION SYSTEMS, 2025, 67 (03) :2935-2965
[50]   FedOCD: A One-Shot Federated Framework for Heterogeneous Cross-Domain Recommendation [J].
Liu, Zhi ;
He, Xiaohua ;
Ma, Xulin ;
Wang, Benfeng ;
Shen, Guojiang ;
Kong, Xiangjie .
WEB AND BIG DATA, APWEB-WAIM 2024, PT IV, 2024, 14964 :69-83