Federated Learning (FL) is a machine learning paradigm that learns from data kept locally to safeguard the privacy of clients, whereas local SGD is typically employed on the clients' devices to improve communication efficiency. However, such a scheme is currently constrained by the slow and unstable convergence induced by clients' heterogeneous data. In this work, we identify three under-explored phenomena of the biased local learning that may explain these challenges caused by local updates in supervised FL. As a remedy, we propose FedAug, a novel unified algorithm that reduces the local learning bias on features and classifiers to tackle these challenges. FedAug consists of two components: AugMean and AugCA. AugMean alleviates the bias in the local classifiers by balancing the output distribution of models. AugCA learns client invariant features that are close to global features but considerably distinct from those learned from other input distributions. In a series of experiments, we show that FedAug consistently outperforms other SOTA FL and domain generalization (DG) baselines, in which both two components (i.e., AugMean and AugCA) have individual performance gains.
翻译:联邦学习(FL)是一种机器学习模式,它从当地保存的数据中学习,以保障客户的隐私,而当地SGD通常在客户的装置上使用,以提高通信效率;然而,目前这种计划受到客户不同数据导致的缓慢和不稳定的趋同的制约。在这项工作中,我们查明了当地有偏见的学习的三个未得到充分探讨的现象,这些现象可能解释当地在受监督的FL更新中出现的这些挑战。作为一种补救措施,我们建议FedAug采用一种新颖的统一算法,减少当地对特征和分类者的学习偏差,以应对这些挑战。 FedAug由两个部分组成:AugMEan和AugCA。AugMEan通过平衡模型的产出分布来减轻当地分类者的偏见。AugMean学习了接近全球特征但与其他投入分布所学到的差别很大的特点。在一系列实验中,我们表明FedAug一直比其他SOTA FL和域通用(DG)基线(即Aug-MEan和AugCA),这两个部分都有个人业绩收益。