在联邦学习中实现分组条件下的可信预测，提升不确定性量化效率。
Efficient Federated Conformal Prediction with Group-Conditional Guarantee
- 通过构建可合并的原子分层核心集，实现分组条件下的联邦校准。
- 在合成与真实数据上达到与集中式校准相当的覆盖率和效率。
- 适合医疗、金融等需跨客户端隐私保护的可信AI场景。
部署可信AI系统需要严格的不确定性量化。符合性预测（Conformal Prediction, CP）是一种广泛使用的框架，可在不依赖分布假设的情况下生成具有覆盖率保证的预测集。在许多实际场景中，如医疗、金融和移动传感，用于CP校准的数据分布在多个客户端，每个客户端具有本地数据分布。在联邦设置下，数据常可划分为可能重叠的组，这些组可能反映客户端特有的分层或交叉属性，如人口统计学或语义类别。本文提出分组条件联邦符合性预测（GC-FCP），是针对预定义组别混合目标的条件符合性校准的联邦扩展。GC-FCP从本地校准得分构建可合并的原子分层核心集，在活跃原子数适中时，可在服务器端实现紧凑聚合。在合成与真实世界数据集上的实验验证了GC-FCP相较于集中式校准基线的性能。代码已开源：https://github.com/HaifengWen/GC-FCP。
原文摘要 · Abstract (English)
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 federated extension of conditional conformal calibration for a target mixture over prespecified groups. GC-FCP constructs mergeable, atom-stratified coresets from local calibration scores, enabling compact aggregation at the server when the number of active atoms is moderate. Experiments on synthetic and real-world datasets validate the performance of GC-FCP compared to centralized calibration baselines. The code of our work can be found at https://github.com/HaifengWen/GC-FCP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。