Federated Computation of ROC and PR Curves
This solves the problem of privacy-preserving model evaluation for federated learning systems, though it is an incremental improvement by adapting existing curve computation methods to a federated setting.
The paper tackles the challenge of computing ROC and PR curves in federated learning where data privacy prevents access to raw prediction scores, proposing a method that estimates quantiles under distributed differential privacy. It achieves high approximation accuracy with minimal communication and strong privacy guarantees on real-world datasets.
Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves are fundamental tools for evaluating machine learning classifiers, offering detailed insights into the trade-offs between true positive rate vs. false positive rate (ROC) or precision vs. recall (PR). However, in Federated Learning (FL) scenarios, where data is distributed across multiple clients, computing these curves is challenging due to privacy and communication constraints. Specifically, the server cannot access raw prediction scores and class labels, which are used to compute the ROC and PR curves in a centralized setting. In this paper, we propose a novel method for approximating ROC and PR curves in a federated setting by estimating quantiles of the prediction score distribution under distributed differential privacy. We provide theoretical bounds on the Area Error (AE) between the true and estimated curves, demonstrating the trade-offs between approximation accuracy, privacy, and communication cost. Empirical results on real-world datasets demonstrate that our method achieves high approximation accuracy with minimal communication and strong privacy guarantees, making it practical for privacy-preserving model evaluation in federated systems.