部署后自适应：通过联邦学习与源-目标远程梯度对齐利用源数据
Post-Deployment Adaptation with Access to Source Data via Federated Learning and Source-Target Remote Gradient Alignment
- University of Oxford（牛津大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对部署后自适应中无法访问源数据的问题，提出FedPDA框架，通过远程梯度交换利用源数据，并引入StarAlign方法对齐源-目标梯度，在医学影像任务中验证了有效性。
AI中文摘要：
深度神经网络在医学影像中的部署受到训练数据与部署后处理数据之间分布偏移的阻碍，导致性能下降。部署后自适应（PDA）通过使用有限的标记或完全未标记的目标数据来调整预训练、已部署的模型以适应目标数据分布，同时假设无法访问源训练数据，因为出于隐私考虑及其庞大体积，这些数据无法随模型一同部署。这使得由于有限的学习信号，可靠的自适应变得具有挑战性。本文挑战了这一假设，并引入了FedPDA，一种新颖的自适应框架，将联邦学习中从远程数据学习的效用引入PDA。FedPDA使部署的模型能够通过远程梯度交换从源数据获取信息，同时旨在专门针对目标域优化模型。针对FedPDA，我们提出了一种新颖的优化方法StarAlign（源-目标远程梯度对齐），该方法通过最大化源-目标域对之间的内积来对齐梯度，以促进学习特定于目标的模型。我们使用多中心数据库在癌症转移检测和皮肤病变分类任务中证明了该方法的有效性，我们的方法与先前工作相比表现更优。代码可在以下网址获取：https://github.com/FelixWag/StarAlign
英文摘要：
Deployment of Deep Neural Networks in medical imaging is hindered by distribution shift between training data and data processed after deployment, causing performance degradation. Post-Deployment Adaptation (PDA) addresses this by tailoring a pre-trained, deployed model to the target data distribution using limited labelled or entirely unlabelled target data, while assuming no access to source training data as they cannot be deployed with the model due to privacy concerns and their large size. This makes reliable adaptation challenging due to limited learning signal. This paper challenges this assumption and introduces FedPDA, a novel adaptation framework that brings the utility of learning from remote data from Federated Learning into PDA. FedPDA enables a deployed model to obtain information from source data via remote gradient exchange, while aiming to optimize the model specifically for the target domain. Tailored for FedPDA, we introduce a novel optimization method StarAlign (Source-Target Remote Gradient Alignment) that aligns gradients between source-target domain pairs by maximizing their inner product, to facilitate learning a target-specific model. We demonstrate the method's effectiveness using multi-center databases for the tasks of cancer metastases detection and skin lesion classification, where our method compares favourably to previous work. Code is available at: https://github.com/FelixWag/StarAlign
