Federated learning achieves joint training of deep models by connecting decentralized data sources, which can significantly mitigate the risk of privacy leakage. However, in a more general case, the distributions of labels among clients are different, called ``label distribution skew''. Directly applying conventional federated learning without consideration of label distribution skew issue significantly hurts the performance of the global model. To this end, we propose a novel federated learning method, named FedMGD, to alleviate the performance degradation caused by the label distribution skew issue. It introduces a global Generative Adversarial Network to model the global data distribution without access to local datasets, so the global model can be trained using the global information of data distribution without privacy leakage. The experimental results demonstrate that our proposed method significantly outperforms the state-of-the-art on several public benchmarks. Code is available at \url{https://github.com/Sheng-T/FedMGD}.
翻译:联邦学习通过将分散的数据源连接起来,实现深层次模型的联合培训,这可以大大降低隐私泄漏的风险。然而,在更一般的情况下,客户之间标签的分布是不同的,称为“标签分发 skew' ” 。直接应用传统的联合学习而不考虑标签分发问题,会大大损害全球模型的性能。为此,我们提议了一个名为FedMGD的新型联合学习方法,以缓解标签分发skew问题造成的性能退化。它引入了一个全球基因自动网络,以模拟全球数据分发,而无需查阅当地数据集,这样全球模型就可以在不泄露隐私的情况下利用全球数据分发信息进行培训。实验结果表明,我们拟议的方法大大优于若干公共基准的状态。代码可在以下https://github.com/Sheng-T/FedMGD}查阅。