TY - GEN
T1 - FedVar
T2 - 37th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2022
AU - Shin, Wooseok
AU - Shin, Jitae
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Among the studies to solve statistical-related problems in federated learning (FL), there are many studies to improve the non-independent and identically distributed (Non-IID) problem of user data. This problem occurs because each local device collects data from different clients, so the size and characteristics of the data are different. When the data distribution of local devices is IID, it does not negatively affect learning, but when non-IID, it does not reach the general cloud computing performance. In this paper, we propose FedVar, an algorithm that uses the weight standard deviation for each client, to improve the situation in which the distribution of data is non-IID, so FL learning is not done properly. In addition, the performance is verified by comparing the acuity and loss of the proposed algorithm with other existing FL algorithms including FedAvg.
AB - Among the studies to solve statistical-related problems in federated learning (FL), there are many studies to improve the non-independent and identically distributed (Non-IID) problem of user data. This problem occurs because each local device collects data from different clients, so the size and characteristics of the data are different. When the data distribution of local devices is IID, it does not negatively affect learning, but when non-IID, it does not reach the general cloud computing performance. In this paper, we propose FedVar, an algorithm that uses the weight standard deviation for each client, to improve the situation in which the distribution of data is non-IID, so FL learning is not done properly. In addition, the performance is verified by comparing the acuity and loss of the proposed algorithm with other existing FL algorithms including FedAvg.
KW - Data Heterogeneity
KW - FedAvg
KW - FedSGD
KW - FedVar
KW - Federated Learning
KW - Non-IID Data
UR - https://www.scopus.com/pages/publications/85140604766
U2 - 10.1109/ITC-CSCC55581.2022.9894899
DO - 10.1109/ITC-CSCC55581.2022.9894899
M3 - Conference contribution
AN - SCOPUS:85140604766
T3 - ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications
SP - 456
EP - 459
BT - ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 5 July 2022 through 8 July 2022
ER -