Skip to main content

Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples

Publication ,  Conference
Sun, J; Xu, Z; Yang, D; Nath, V; Li, W; Zhao, C; Xu, D; Chen, Y; Roth, HR
Published in: Proceedings of the IEEE International Conference on Computer Vision
January 1, 2023

Federated learning is a popular collaborative learning approach that enables clients to train a global model without sharing their local data. Vertical federated learning (VFL) deals with scenarios in which the data on clients have different feature spaces but share some overlapping samples. Existing VFL approaches suffer from high communication costs and cannot deal efficiently with limited overlapping samples commonly seen in the real world. We propose a practical VFL framework called one-shot VFL that can solve the communication bottleneck and the problem of limited overlapping samples simultaneously based on semi-supervised learning. We also propose few-shot VFL to improve the accuracy further with just one more communication round between the server and the clients. In our proposed framework, the clients only need to communicate with the server once or only a few times. We evaluate the proposed VFL framework on both image and tabular datasets. Our methods can improve the accuracy by more than 46.5% and reduce the communication cost by more than 330× compared with state-of-the-art VFL methods when evaluated on CIFAR-10. Our code is available at https://nvidia.github.io/NVFlare/research/one-shot-vfl.

Duke Scholars

Published In

Proceedings of the IEEE International Conference on Computer Vision

DOI

ISSN

1550-5499

Publication Date

January 1, 2023

Start / End Page

5180 / 5189
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Sun, J., Xu, Z., Yang, D., Nath, V., Li, W., Zhao, C., … Roth, H. R. (2023). Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples. In Proceedings of the IEEE International Conference on Computer Vision (pp. 5180–5189). https://doi.org/10.1109/ICCV51070.2023.00480
Sun, J., Z. Xu, D. Yang, V. Nath, W. Li, C. Zhao, D. Xu, Y. Chen, and H. R. Roth. “Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples.” In Proceedings of the IEEE International Conference on Computer Vision, 5180–89, 2023. https://doi.org/10.1109/ICCV51070.2023.00480.
Sun J, Xu Z, Yang D, Nath V, Li W, Zhao C, et al. Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples. In: Proceedings of the IEEE International Conference on Computer Vision. 2023. p. 5180–9.
Sun, J., et al. “Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples.” Proceedings of the IEEE International Conference on Computer Vision, 2023, pp. 5180–89. Scopus, doi:10.1109/ICCV51070.2023.00480.
Sun J, Xu Z, Yang D, Nath V, Li W, Zhao C, Xu D, Chen Y, Roth HR. Communication-Efficient Vertical Federated Learning with Limited Overlapping Samples. Proceedings of the IEEE International Conference on Computer Vision. 2023. p. 5180–5189.

Published In

Proceedings of the IEEE International Conference on Computer Vision

DOI

ISSN

1550-5499

Publication Date

January 1, 2023

Start / End Page

5180 / 5189