论文标题
DEARFSAC：通过深入的强化学习优化不可靠的联邦学习的方法
DearFSAC: An Approach to Optimizing Unreliable Federated Learning via Deep Reinforcement Learning
论文作者
论文摘要
在联合学习（FL）中，模型聚合已被广泛用于数据隐私。近年来，将不同的权重分配给本地模型已被用来减轻本地数据集之间差异引起的FL性能降解。但是，当各种缺陷使FL过程不可靠时，大多数现有的FL方法暴露了弱鲁棒性。在本文中，我们提出了缺陷感知的联合软性角色批判者（Dearfsac），以动态分配权重，以改善FL的鲁棒性。深厚的增强学习算法软参与者批评是为了近乎最佳的性能和稳定的收敛性。此外，对自动编码器进行了训练，可以输出低维嵌入向量，这些向量被进一步用于评估模型质量。在实验中，DearFSAC在四个数据集上的三种现有方法在有缺陷的情况下的四个数据集上的三种现有方法（IID）和非IID设置。
In federated learning (FL), model aggregation has been widely adopted for data privacy. In recent years, assigning different weights to local models has been used to alleviate the FL performance degradation caused by differences between local datasets. However, when various defects make the FL process unreliable, most existing FL approaches expose weak robustness. In this paper, we propose the DEfect-AwaRe federated soft actor-critic (DearFSAC) to dynamically assign weights to local models to improve the robustness of FL. The deep reinforcement learning algorithm soft actor-critic is adopted for near-optimal performance and stable convergence. Besides, an auto-encoder is trained to output low-dimensional embedding vectors that are further utilized to evaluate model quality. In the experiments, DearFSAC outperforms three existing approaches on four datasets for both independent and identically distributed (IID) and non-IID settings under defective scenarios.
