Trading Off Privacy, Utility and Efficiency in Federated Learning
This work addresses the challenge for federated learning practitioners in selecting protection mechanisms by quantifying trade-offs, though it is incremental as it builds on existing methods.
The authors tackled the problem of balancing privacy, utility, and efficiency in federated learning by proposing a unified framework and formulating trade-offs, leading to a No-Free-Lunch theorem that shows it is unrealistic to achieve all three simultaneously in certain scenarios, with analysis providing lower bounds for common protection mechanisms.
Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing requirements in preserving \textit{privacy} and maintaining high model \textit{utility}. In addition, it is a mandate for a federated learning system to achieve high \textit{efficiency} in order to enable large-scale model training and deployment. We propose a unified federated learning framework that reconciles horizontal and vertical federated learning. Based on this framework, we formulate and quantify the trade-offs between privacy leakage, utility loss, and efficiency reduction, which leads us to the No-Free-Lunch (NFL) theorem for the federated learning system. NFL indicates that it is unrealistic to expect an FL algorithm to simultaneously provide excellent privacy, utility, and efficiency in certain scenarios. We then analyze the lower bounds for the privacy leakage, utility loss and efficiency reduction for several widely-adopted protection mechanisms including \textit{Randomization}, \textit{Homomorphic Encryption}, \textit{Secret Sharing} and \textit{Compression}. Our analysis could serve as a guide for selecting protection parameters to meet particular requirements.