Efficient Federated Conformal Prediction with Group-Conditional Guarantee
This addresses the need for trustworthy AI in domains like healthcare and finance by enabling efficient federated conformal prediction with group-specific coverage, though it appears incremental as an extension of existing federated methods.
The paper tackled the problem of providing uncertainty quantification with group-conditional guarantees in federated settings, where calibration data is distributed across clients, and proposed GC-FCP, which achieved validated performance on synthetic and real-world datasets.
Deploying trustworthy AI systems requires principled uncertainty quantification. Conformal prediction (CP) is a widely used framework for constructing prediction sets with distribution-free coverage guarantees. In many practical settings, including healthcare, finance, and mobile sensing, the calibration data required for CP are distributed across multiple clients, each with its own local data distribution. In this federated setting, data can often be partitioned into, potentially overlapping, groups, which may reflect client-specific strata or cross-cutting attributes such as demographic or semantic categories. We propose group-conditional federated conformal prediction (GC-FCP), a novel protocol that provides group-conditional coverage guarantees. GC-FCP constructs mergeable, group-stratified coresets from local calibration scores, enabling clients to communicate compact weighted summaries that support efficient aggregation and calibration at the server. Experiments on synthetic and real-world datasets validate the performance of GC-FCP compared to centralized calibration baselines.