发表机构
University of Glasgow（格拉斯哥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对婴儿运动分析中集中式训练的数据隐私问题，提出首个联邦学习框架，并引入不确定性感知的联邦平均策略，在不集中数据下达到接近集中式训练的性能。
AI 中文摘要
婴儿运动分析为神经发育障碍的早期识别提供了有价值的生物标志物。近年来，深度学习的进展使得从视频衍生的骨骼表示中自动分析婴儿运动成为可能，在全身运动评估（GMA）等任务上达到了与专家评估相当的性能。然而，现有的大多数方法依赖于集中式训练，需要将来自多个机构的数据收集并存储在单一地点。由于隐私、治理和数据共享的限制，这种假设在临床环境中往往不切实际。为了解决这些挑战，我们提出了据我们所知的第一个用于自动婴儿运动分析和全身运动评估的联邦学习框架，该框架使用骨骼运动数据。作为临床相关的用例，所提出的框架在不安运动分类上进行了评估。为了量化模型置信度，在推理过程中采用蒙特卡洛（MC）Dropout来估计预测不确定性。在此基础上，我们提出了一种不确定性感知的联邦平均（UA-FedAvg）策略，该策略将MC-Dropout导出的预测熵纳入联邦聚合过程，使得客户端贡献能够根据其预测不确定性进行调整。实验采用跨受试者评估协议，在三客户端联邦学习设置下进行。结果表明，与独立训练的本地模型相比，联邦学习显著提高了分类性能，同时达到了接近集中式训练的性能。此外，UA-FedAvg及其结合验证损失的变体在评估的数据划分配置中通常优于传统的FedAvg。
英文摘要
Infant movement analysis provides valuable biomarkers for the early identification of neurodevelopmental disorders. Recent advances in deep learning have enabled automated analysis of infant movements from video-derived skeletal representations, achieving performance comparable to expert assessment for tasks such as General Movement Assessment (GMA). However, most existing approaches rely on centralized training, requiring data from multiple institutions to be collected and stored at a single site. Such assumptions are often impractical in clinical settings due to privacy, governance, and data-sharing constraints. To address these challenges, we present, to the best of our knowledge, the first federated learning framework for automated infant movement analysis and General Movement Assessment using skeletal motion data. As a clinically relevant use case, the proposed framework is evaluated on fidgety movement classification. To quantify model confidence, Monte Carlo (MC) Dropout is employed to estimate predictive uncertainty during inference. Building upon this, we propose an Uncertainty-Aware Federated Averaging (UA-FedAvg) strategy that incorporates predictive entropy derived from MC-Dropout into the federated aggregation process, enabling client contributions to be adjusted according to their predictive uncertainty. Experiments were conducted using a cross-subject evaluation protocol under a three-client federated learning setting. Results demonstrate that federated learning substantially improves classification performance compared with independently trained local models while achieving performance approaching that of centralized training. Furthermore, UA-FedAvg and its variant incorporating validation loss generally outperform conventional FedAvg across the evaluated data-split configurations.
CommentsAccepted at IEEE The 4th International Conference on Federated Learning Technologies and Applications (FLTA26)
