Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation
This work expands the applicability of differential privacy in federated learning, offering an efficient and practical solution for privacy-preserving learning in distributed systems with partial participation, though it is incremental as it builds on existing full-participation methods.
This paper tackled the challenge of achieving differential privacy in federated learning under partial-participation scenarios, where only a subset of machines participate each time-step, by introducing a noise-cancellation mechanism that preserves privacy without sacrificing convergence rates or computational efficiency, showing optimal performance for both homogeneous and heterogeneous data distributions.
This paper tackles the challenge of achieving Differential Privacy (DP) in Federated Learning (FL) under partial-participation, where only a subset of the machines participate in each time-step. While previous work achieved optimal performance in full-participation settings, these methods struggled to extend to partial-participation scenarios. Our approach fills this gap by introducing a novel noise-cancellation mechanism that preserves privacy without sacrificing convergence rates or computational efficiency. We analyze our method within the Stochastic Convex Optimization (SCO) framework and show that it delivers optimal performance for both homogeneous and heterogeneous data distributions. This work expands the applicability of DP in FL, offering an efficient and practical solution for privacy-preserving learning in distributed systems with partial participation.