Federated learning (FL) aims to learn joint knowledge from a large scale of decentralized devices with labeled data in a privacy-preserving manner. However, since high-quality labeled data require expensive human intelligence and efforts, data with incorrect labels (called noisy labels) are ubiquitous in reality, which inevitably cause performance degradation. Although a lot of methods are proposed to directly deal with noisy labels, these methods either require excessive computation overhead or violate the privacy protection principle of FL. To this end, we focus on this issue in FL with the purpose of alleviating performance degradation yielded by noisy labels meanwhile guaranteeing data privacy. Specifically, we propose a Local Self-Regularization method, which effectively regularizes the local training process via implicitly hindering the model from memorizing noisy labels and explicitly narrowing the model output discrepancy between original and augmented instances using self distillation. Experimental results demonstrate that our proposed method can achieve notable resistance against noisy labels in various noise levels on three benchmark datasets. In addition, we integrate our method with existing state-of-the-arts and achieve superior performance on the real-world dataset Clothing1M. The code is available at https://github.com/Sprinter1999/FedLSR.
翻译:联邦学习(FL)的目的是以保密的方式,从大规模分散的装置中学习共同知识,用贴有标签的数据进行保密保存,但是,由于高质量的标签数据要求花费昂贵的人类情报和努力,高质量的标签数据需要花费昂贵的人类情报和努力,因此,不正确的标签(所谓噪音标签)数据在现实中是无处不在的,不可避免地导致业绩退化。虽然提出了许多方法来直接处理噪音标签,但这些方法需要过高的计算间接费用或违反FL的隐私保护原则。为此,我们在FL集中关注这一问题,目的是减轻由保障数据隐私的噪音标签和保障数据隐私的噪音标签造成的性能退化。具体地说,我们建议一种地方自重标签(所谓噪音标签)的数据在现实中普遍存在,从而隐含地阻碍模型,使不正确标签(所谓噪音标签)的数据在现实中普遍存在,明确缩小原始和扩充后使用自我蒸馏的方式之间的模型产出差异。实验结果表明,我们提出的方法可以在三个基准数据集的各个噪音级别上取得显著的抗力。此外,我们还将我们的方法与现有的艺术品状态相结合,在现实-1999年/Fsmarisflam1M/M.