Federated Learning has become a widely-used framework which allows learning a global model on decentralized local datasets under the condition of protecting local data privacy. However, federated learning faces severe optimization difficulty when training samples are not independently and identically distributed (non-i.i.d.). In this paper, we point out that the client sampling practice plays a decisive role in the aforementioned optimization difficulty. We find that the negative client sampling will cause the merged data distribution of currently sampled clients heavily inconsistent with that of all available clients, and further make the aggregated gradient unreliable. To address this issue, we propose a novel learning rate adaptation mechanism to adaptively adjust the server learning rate for the aggregated gradient in each round, according to the consistency between the merged data distribution of currently sampled clients and that of all available clients. Specifically, we make theoretical deductions to find a meaningful and robust indicator that is positively related to the optimal server learning rate and can effectively reflect the merged data distribution of sampled clients, and we utilize it for the server learning rate adaptation. Extensive experiments on multiple image and text classification tasks validate the great effectiveness of our method.
翻译:联邦学习已经成为一个广泛使用的框架,它使得在保护当地数据隐私的条件下学习分散的地方数据集全球模型成为可以学习的一种全球模式,然而,当培训样本不是独立和同样分布(非i.i.d.)时,联邦学习面临着严重的优化困难。在本文件中,我们指出客户抽样做法在上述优化困难中起着决定性作用。我们发现,负面客户抽样将造成目前抽样客户的数据分配与所有现有客户的数据分配严重不一致,并进一步使汇总梯度变得不可靠。为了解决这一问题,我们建议建立一个新的学习率适应机制,以适应性调整每轮总梯度的服务器学习率,根据目前抽样客户和所有现有客户的合并数据分配的一致性。具体地说,我们进行理论推算,以找到一个与最佳服务器学习率积极相关的有意义和有力的指标,并能够有效地反映抽样客户的合并数据分配情况,我们用它来适应服务器学习率。关于多种图像和文本分类任务的广泛实验证实了我们的方法的巨大有效性。