Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints
Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints
复制标题
间歇客户可用性和时变通信约束下的联邦学习
DOI：
10.1109/jstsp.2022.3224590
复制
发表时间：
2022-05
影响因子：
7.5
通讯作者：
Mónica Ribero;H. Vikalo;G. Veciana
中科院分区：
文献类型：
--
作者：
Mónica Ribero;H. Vikalo;G. Veciana
联合学习系统促进了在具有潜在异构数据的大量分布式边缘设备上训练全局模型。这样的系统在具有间歇性客户端可用性和/或时变通信约束的资源受限设置中操作。因此，由联邦学习系统训练的全局模型可能偏向于具有更高可用性的客户端。我们提出了联邦平均辅助自适应采样技术（F3 ast），一个无偏的算法，动态学习的可用性相关的客户端选择策略，渐近最大限度地减少客户端采样方差对全局模型的收敛性的影响，提高联邦学习的性能。所提出的算法进行了测试，在各种设置下间歇性可用的客户端在通信约束下运行，其有效性证明了合成数据和现实的联邦基准测试实验使用CIFAR 100和莎士比亚数据集。我们报告的准确性比FedAvg提高了186%和8%，比FedAdamon CIFAR 100和Shakespeare分别提高了8%和7%。
Federated learning systems facilitate the training of global models across large numbers of distributed edge-devices with potentially heterogeneous data. Such systems operate in resource constrained settings with intermittent client availability and/or time-varying communication constraints. As a result, the global models trained by federated learning systems may be biased towards clients with higher availability. We propose Federated Averaging Aided by an Adaptive Sampling Technique (F3ast), an unbiased algorithm that dynamically learns an availability-dependent client selection strategy which asymptotically minimizes the impact of client-sampling variance on the global model's convergence, enhancing performance of federated learning. The proposed algorithm is tested in a variety of settings for intermittently available clients operating under communication constraints, and its efficacy demonstrated on synthetic data and realistically federated benchmarking experiments using CIFAR100 and Shakespeare datasets. We report up to 186% and 8% accuracy improvements over FedAvg, and 8% and 7% over FedAdamon CIFAR100 and Shakespeare, respectively.