Skip to main content

FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning

Publication ,  Conference
Tang, M; Ning, X; Wang, Y; Sun, J; Li, H; Chen, Y
Published in: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
January 1, 2022

Client-wise data heterogeneity is one of the major issues that hinder effective training in federated learning (FL). Since the data distribution on each client may vary dramatically, the client selection strategy can significantly influence the convergence rate of the FL process. Active client selection strategies are popularly proposed in recent studies. However, they neglect the loss correlations between the clients and achieve only marginal improvement compared to the uniform selection strategy. In this work, we propose FedCoran FLframework built on a correlation-based client selection strategy, to boost the convergence rate of FL. Specifically, we first model the loss correlations between the clients with a Gaussian Process (GP). Based on the GP model, we derive a client selection strategy with a significant reduction of expected global loss in each round. Besides, we develop an efficient GP training method with a low communication overhead in the FL scenario by utilizing the covariance stationarity. Our experimental results show that compared to the state-of-the-art method, FedCorr can improve the convergence rates by 34% 99% and 26% 51% on FMNIST and CIFAR-10, respectively.

Duke Scholars

Published In

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

DOI

ISSN

1063-6919

ISBN

9781665469463

Publication Date

January 1, 2022

Volume

2022-June

Start / End Page

10092 / 10101
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Tang, M., Ning, X., Wang, Y., Sun, J., Li, H., & Chen, Y. (2022). FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Vol. 2022-June, pp. 10092–10101). https://doi.org/10.1109/CVPR52688.2022.00986
Tang, M., X. Ning, Y. Wang, J. Sun, H. Li, and Y. Chen. “FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning.” In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2022-June:10092–101, 2022. https://doi.org/10.1109/CVPR52688.2022.00986.
Tang M, Ning X, Wang Y, Sun J, Li H, Chen Y. FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2022. p. 10092–101.
Tang, M., et al. “FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning.” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2022-June, 2022, pp. 10092–101. Scopus, doi:10.1109/CVPR52688.2022.00986.
Tang M, Ning X, Wang Y, Sun J, Li H, Chen Y. FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2022. p. 10092–10101.

Published In

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

DOI

ISSN

1063-6919

ISBN

9781665469463

Publication Date

January 1, 2022

Volume

2022-June

Start / End Page

10092 / 10101