论文标题
FEDDRL：在联合学习中针对非IID数据的深入增强学习的自适应聚合
FedDRL: Deep Reinforcement Learning-based Adaptive Aggregation for Non-IID Data in Federated Learning
论文作者
论文摘要
跨不同边缘设备（客户）局部数据的分布不均匀，导致模型训练缓慢，并降低了联合学习的准确性。幼稚的联合学习（FL）策略和大多数替代解决方案试图通过加权跨客户的深度学习模型来实现更多公平性。这项工作介绍了在现实世界数据集中遇到的一种新颖的非IID类型，即集群键，其中客户组具有具有相似分布的本地数据，从而导致全局模型收敛到过度拟合的解决方案。为了处理非IID数据，尤其是群集相干数据，我们提出了FedDrl，这是一种新型的FL模型，该模型采用深度强化学习来适应每个客户的影响因素（将用作聚合过程中的权重）。在一组联合数据集上进行了广泛的实验，证实，拟议的FEDDR对FedAvg和FedProx方法有利，例如，CIFAR-100数据集的平均最高为4.05％和2.17％。
The uneven distribution of local data across different edge devices (clients) results in slow model training and accuracy reduction in federated learning. Naive federated learning (FL) strategy and most alternative solutions attempted to achieve more fairness by weighted aggregating deep learning models across clients. This work introduces a novel non-IID type encountered in real-world datasets, namely cluster-skew, in which groups of clients have local data with similar distributions, causing the global model to converge to an over-fitted solution. To deal with non-IID data, particularly the cluster-skewed data, we propose FedDRL, a novel FL model that employs deep reinforcement learning to adaptively determine each client's impact factor (which will be used as the weights in the aggregation process). Extensive experiments on a suite of federated datasets confirm that the proposed FedDRL improves favorably against FedAvg and FedProx methods, e.g., up to 4.05% and 2.17% on average for the CIFAR-100 dataset, respectively.
