In this work, we propose a fast adaptive federated meta-learning (FAM) framework for collaboratively learning a single global model, which can then be personalized locally on individual clients. Federated learning enables multiple clients to collaborate to train a model without sharing data. Clients with insufficient data or data diversity participate in federated learning to learn a model with superior performance. Nonetheless, learning suffers when data distributions diverge. There is a need to learn a global model that can be adapted using client's specific information to create personalized models on clients is required. MRI data suffers from this problem, wherein, one, due to data acquisition challenges, local data at a site is sufficient for training an accurate model and two, there is a restriction of data sharing due to privacy concerns and three, there is a need for personalization of a learnt shared global model on account of domain shift across client sites. The global model is sparse and captures the common features in the MRI. This skeleton network is grown on each client to train a personalized model by learning additional client-specific parameters from local data. Experimental results show that the personalization process at each client quickly converges using a limited number of epochs. The personalized client models outperformed the locally trained models, demonstrating the efficacy of the FAM mechanism. Additionally, the sparse parameter set to be communicated during federated learning drastically reduced communication overhead, which makes the scheme viable for networks with limited resources.

翻译：在本工作中，我们提出了一种快速自适应联邦元学习（FAM）框架，用于协同学习一个全局模型，该模型随后可在各个客户端上进行本地个性化。联邦学习使多个客户端能够在无需共享数据的情况下协作训练模型。数据不足或数据多样性有限的客户端通过参与联邦学习来学习性能更优的模型。然而，当数据分布存在差异时，学习过程会受到影响。因此，需要学习一个能够利用客户端特定信息进行适配的全局模型，从而在客户端上创建个性化模型。MRI数据面临这一问题：其一，由于数据采集困难，单个站点的本地数据不足以训练精确模型；其二，因隐私问题存在数据共享限制；其三，由于客户端站点间的域偏移，需要对学习到的共享全局模型进行个性化。该全局模型是稀疏的，能够捕获MRI中的共同特征。这一骨架网络在每个客户端上通过从本地数据中学习额外的客户端特定参数进行扩展，以训练个性化模型。实验结果表明，每个客户端的个性化过程在有限训练轮次内快速收敛。个性化客户端模型的性能优于本地训练模型，验证了FAM机制的有效性。此外，联邦学习过程中需通信的稀疏参数集大幅降低了通信开销，使得该方案适用于资源受限的网络环境。