为医疗联邦学习设计不确定性感知的特征补全方法，提升模型可靠性。
Probabilistic Feature Imputation and Uncertainty-Aware Multimodal Federated Aggregation
- 用概率化网络输出带置信度的缺失模态特征补全结果
- 在最差配置下实现AUC提升5.36%，优于确定性基线
- 适合对可靠性要求高的医疗联邦学习场景
多模态联邦学习可在保护隐私的前提下实现跨医疗机构协同建模，但因模态异构性面临挑战：许多临床机构因资源或流程差异仅具备部分模态。现有方法通过特征补全网络合成缺失模态表示，但仅输出点估计且无可信度衡量，使下游分类器误将所有补全特征视为等可靠。在高风险医疗应用中，此缺陷带来显著风险。本文提出概率特征补全网络（P-FIN），输出校准后的不确定性估计，并在两层利用：(1) 局部层面，通过Sigmoid门控抑制不可靠特征维度；(2) 全局层面，采用Fed-UQ-Avg聚合策略，优先采纳可信度高的客户端更新。在使用CheXpert、NIH Open-I和PadChest数据集的联邦胸部X光分类实验中，相较确定性基线实现持续改进，最困难配置下AUC提升5.36%。
原文摘要 · Abstract (English)
Multimodal federated learning enables privacy-preserving collaborative model training across healthcare institutions. However, a fundamental challenge arises from modality heterogeneity: many clinical sites possess only a subset of modalities due to resource constraints or workflow variations. Existing approaches address this through feature imputation networks that synthesize missing modality representations, yet these methods produce point estimates without reliability measures, forcing downstream classifiers to treat all imputed features as equally trustworthy. In safety-critical medical applications, this limitation poses significant risks. We propose the Probabilistic Feature Imputation Network (P-FIN), which outputs calibrated uncertainty estimates alongside imputed features. This uncertainty is leveraged at two levels: (1) locally, through sigmoid gating that attenuates unreliable feature dimensions before classification, and (2) globally, through Fed-UQ-Avg, an aggregation strategy that prioritizes updates from clients with reliable imputation. Experiments on federated chest X-ray classification using CheXpert, NIH Open-I, and PadChest demonstrate consistent improvements over deterministic baselines, with +5.36% AUC gain in the most challenging configuration.
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。