Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation

Roie Reshef, Kfir Yehuda Levy
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:51503-51530, 2025.

Abstract

This paper addresses the challenge of achieving Differential Privacy (DP) in Federated Learning (FL) under the partial-participation setting, where each machine participates in only some of training rounds. While earlier work achieved optimal performance and efficiency in full-participation scenarios, these methods could not extend effectively to cases with partial-participation. Our approach addresses this gap by introducing a novel noise-cancellation mechanism that ensures privacy without compromising convergence rates or computational efficiency. We analyze our method within the Stochastic Convex Optimization (SCO) framework and demonstrate that it achieves optimal performance for both homogeneous and heterogeneous data distributions. This work broadens the applicability of DP in FL, providing a practical and efficient solution for privacy-preserving learning in distributed systems with partial participation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-reshef25a, title = {Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation}, author = {Reshef, Roie and Levy, Kfir Yehuda}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {51503--51530}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/reshef25a/reshef25a.pdf}, url = {https://proceedings.mlr.press/v267/reshef25a.html}, abstract = {This paper addresses the challenge of achieving Differential Privacy (DP) in Federated Learning (FL) under the partial-participation setting, where each machine participates in only some of training rounds. While earlier work achieved optimal performance and efficiency in full-participation scenarios, these methods could not extend effectively to cases with partial-participation. Our approach addresses this gap by introducing a novel noise-cancellation mechanism that ensures privacy without compromising convergence rates or computational efficiency. We analyze our method within the Stochastic Convex Optimization (SCO) framework and demonstrate that it achieves optimal performance for both homogeneous and heterogeneous data distributions. This work broadens the applicability of DP in FL, providing a practical and efficient solution for privacy-preserving learning in distributed systems with partial participation.} }
Endnote
%0 Conference Paper %T Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation %A Roie Reshef %A Kfir Yehuda Levy %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-reshef25a %I PMLR %P 51503--51530 %U https://proceedings.mlr.press/v267/reshef25a.html %V 267 %X This paper addresses the challenge of achieving Differential Privacy (DP) in Federated Learning (FL) under the partial-participation setting, where each machine participates in only some of training rounds. While earlier work achieved optimal performance and efficiency in full-participation scenarios, these methods could not extend effectively to cases with partial-participation. Our approach addresses this gap by introducing a novel noise-cancellation mechanism that ensures privacy without compromising convergence rates or computational efficiency. We analyze our method within the Stochastic Convex Optimization (SCO) framework and demonstrate that it achieves optimal performance for both homogeneous and heterogeneous data distributions. This work broadens the applicability of DP in FL, providing a practical and efficient solution for privacy-preserving learning in distributed systems with partial participation.
APA
Reshef, R. & Levy, K.Y.. (2025). Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:51503-51530 Available from https://proceedings.mlr.press/v267/reshef25a.html.

Related Material