Personalized Federated Learning over non-IID Data for Indoor Localization

被引:16
作者
Wu, Peng [1 ]
Imbiriba, Tales [1 ]
Park, Junha [2 ]
Kim, Sunwoo [2 ]
Closas, Pau [1 ]
机构
[1] Northeastern Univ, Elect & Comp Engn Dept, Boston, MA 02115 USA
[2] Hanyang Univ, Dept Elect Engn, Seoul, South Korea
来源
SPAWC 2021: 2021 IEEE 22ND INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (IEEE SPAWC 2021) | 2020年
关键词
Federated Learning; Bayesian inference; non-IID; data-driven; localization;
D O I
10.1109/SPAWC51858.2021.9593115
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Localization and tracking of objects using data-driven methods is a popular topic due to the complexity in characterizing the physics of wireless channel propagation models. In these modeling approaches, data needs to be gathered to accurately train models, at the same time that user's privacy is maintained. An appealing scheme to cooperatively achieve these goals is known as Federated Learning (FL). A challenge in FL schemes is the presence of non-independent and identically distributed (non-IID) data, caused by unevenly exploration of different areas. In this paper, we consider the use of recent FL schemes to train a set of personalized models that are then optimally fused through Bayesian rules, which makes it appropriate in the context of indoor localization.
引用
收藏
页码:421 / 425
页数:5
相关论文
共 20 条
[1]   Crowd-Based Learning of Spatial Fields for the Internet of Things From harvesting of data to inference [J].
Arias-de-Reyna, Eva ;
Closas, Pau ;
Dardari, Davide ;
Djuric, Petar M. .
IEEE SIGNAL PROCESSING MAGAZINE, 2018, 35 (05) :130-139
[2]  
Ciftler BS, 2020, INT WIREL COMMUN, P2112, DOI 10.1109/IWCMC48107.2020.9148111
[3]   Indoor Tracking: Theory, Methods, and Technologies [J].
Dardari, Davide ;
Closas, Pau ;
Djuric, Petar M. .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2015, 64 (04) :1263-1278
[4]  
Fallah Alireza, 2020, ABS200207948 ARXIV
[5]  
Hsu T.-M. H., 2019, ARXIV1909
[6]  
Huang YT, 2021, AAAI CONF ARTIF INTE, V35, P7865
[7]  
Ji S., 2021, ABS210212920 ARXIV
[8]  
Karimireddy SP, 2020, PR MACH LEARN RES, V119
[9]  
Kulkarni V, 2020, PROCEEDINGS OF THE 2020 FOURTH WORLD CONFERENCE ON SMART TRENDS IN SYSTEMS, SECURITY AND SUSTAINABILITY (WORLDS4 2020), P794, DOI [10.1109/worlds450073.2020.9210355, 10.1109/WorldS450073.2020.9210355]
[10]  
Li Q., 2021, ARXIV210202079