摘要
With the rapidly growing of location-based social networks, point-of-interest (POI) rec-ommendation has been attracting tremendous attentions. Previous works for POI recom-mendation usually use matrix factorization (MF)-based methods, which achieve promising performance. However, existing MF-based methods suffer from two critical limitations: (1) Privacy issues: all users' sensitive data are collected to the centralized server which may leak on either the server side or during transmission. (2) Poor resource utilization and training efficiency: training on centralized server with potentially huge low-rank matrices is computational inefficient. In this paper, we propose a novel decentralized gradient -quantization based matrix factorization (DGMF) framework to address the above limita-tions in POI recommendation. Compared with the centralized MF methods which store all sensitive data and low-rank matrices during model training, DGMF treats each user's de-vice (e.g., phone) as an independent learner and keeps the sensitive data on each user's end. Furthermore, a privacy-preserving and communication-efficient mechanism with gradient -quantization technique is presented to train the proposed model, which aims to handle the privacy problem and reduces the communication cost in the decentralized setting. Theoret-ical guarantees of the proposed algorithm and experimental studies on real-world datasets demonstrate the effectiveness of the proposed algorithm.
- Fine-Grained Preference-Aware Personalized Federated POI Recommendation with Data SparsityZhang, Xiao; Ye, Ziming; Lu, Jianfeng; Zhuang, Fuzhen; Zheng, Yanwei; Yu, Dongxiao*46th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), Taipei, TAIWAN, 2023-07-23 To 2023-07-27.
- Killing two birds with one stone: Quantization achieves privacy in distributed learningYan, Guangfeng; Li, Tan; Wu, Kui; Song, Linqi*Digital Signal Processing: A Review Journal , 2024, 146: 104353.
- Personalized Federated Recommendation via Joint Representation Learning, User Clustering, and Model AdaptationLuo, Sichun; Xiao, Yuanzhang; Song, Linqi*31st ACM International Conference on Information and Knowledge Management (CIKM), Atlanta, GA, 2022-10-17 To 2022-10-21.被引 2
