论文标题
FedControl：当控制理论符合联合学习时
FedControl: When Control Theory Meets Federated Learning
论文作者
论文摘要
迄今为止，最受欢迎的联邦学习算法使用模型参数的坐标为平均。根据本地学习的表现及其发展，我们通过区分客户的贡献来偏离这种方法。该技术的灵感来自控制理论，其分类性能在IID框架中进行了广泛的评估，并与FedAvg进行了比较。
To date, the most popular federated learning algorithms use coordinate-wise averaging of the model parameters. We depart from this approach by differentiating client contributions according to the performance of local learning and its evolution. The technique is inspired from control theory and its classification performance is evaluated extensively in IID framework and compared with FedAvg.
