TY - GEN
T1 - FEDNS
T2 - 2021 IEEE International Conference on Multimedia and Expo, ICME 2021
AU - Zhuo, Yaoxin
AU - Li, Baoxin
N1 - Funding Information: The work was supported in part by a grant from ONR (N00014-19-1-2119). Any opinions expressed in this material are those of the authors and do not necessarily reflect the views of ONR. Publisher Copyright: © 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model collaboratively with the help of a centralized server. The most popular FL algorithm is Federated Averaging (FedAvg), which is based on taking weighted average of the client models, with the weights determined largely based on dataset sizes at the clients. In this paper, we propose a new approach, termed Federated Node Selection (FedNS), for the server's global model aggregation in the FL setting. FedNS filters and re-weights the clients' models at the node/kernel level, hence leading to a potentially better global model by fusing the best components of the clients. Using collaborative image classification as an example, we show with experiments from multiple datasets and networks that FedNS can consistently achieve improved performance over FedAvg.
AB - Federated Learning (FL) is a paradigm that aims to support loosely connected clients in learning a global model collaboratively with the help of a centralized server. The most popular FL algorithm is Federated Averaging (FedAvg), which is based on taking weighted average of the client models, with the weights determined largely based on dataset sizes at the clients. In this paper, we propose a new approach, termed Federated Node Selection (FedNS), for the server's global model aggregation in the FL setting. FedNS filters and re-weights the clients' models at the node/kernel level, hence leading to a potentially better global model by fusing the best components of the clients. Using collaborative image classification as an example, we show with experiments from multiple datasets and networks that FedNS can consistently achieve improved performance over FedAvg.
KW - Federated learning
KW - Image classification
KW - Model aggregation
UR - http://www.scopus.com/inward/record.url?scp=85126462160&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126462160&partnerID=8YFLogxK
U2 - 10.1109/ICME51207.2021.9428075
DO - 10.1109/ICME51207.2021.9428075
M3 - Conference contribution
T3 - Proceedings - IEEE International Conference on Multimedia and Expo
BT - 2021 IEEE International Conference on Multimedia and Expo, ICME 2021
PB - IEEE Computer Society
Y2 - 5 July 2021 through 9 July 2021
ER -