Theoretically Principled Federated Learning for Balancing Privacy and Utility
This work addresses privacy-preservation challenges in federated learning for applications like healthcare or finance, but it is incremental as it builds on existing distortion-based methods.
The paper tackles the problem of balancing privacy and utility in federated learning by proposing a framework that distorts model parameters to achieve personalized trade-offs, with theoretical guarantees of sub-linear utility loss and empirical results showing better utility than baselines under the same privacy budget.
We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary privacy measurements that maps from the distortion to a real value. It can achieve personalized utility-privacy trade-off for each model parameter, on each client, at each communication round in federated learning. Such adaptive and fine-grained protection can improve the effectiveness of privacy-preserved federated learning. Theoretically, we show that gap between the utility loss of the protection hyperparameter output by our algorithm and that of the optimal protection hyperparameter is sub-linear in the total number of iterations. The sublinearity of our algorithm indicates that the average gap between the performance of our algorithm and that of the optimal performance goes to zero when the number of iterations goes to infinity. Further, we provide the convergence rate of our proposed algorithm. We conduct empirical results on benchmark datasets to verify that our method achieves better utility than the baseline methods under the same privacy budget.