论文标题
Statmix：依赖联盟学习中图像统计数据的数据增强方法
StatMix: Data augmentation method that relies on image statistics in federated learning
论文作者
论文摘要
大量注释数据的可用性是深度学习成功的支柱之一。尽管已经提供了许多大数据集进行研究，但是在现实生活中通常并非如此（例如，由于GDPR或与知识产权保护有关的问题，公司无法共享数据）。联合学习（FL）是解决此问题的潜在解决方案，因为它可以对散布在多个节点的数据进行培训，而无需共享本地数据本身。但是，即使无法正确处理，即使是FL方法也会对数据隐私构成威胁。因此，我们提出了使用图像统计数据来改善FL方案结果的增强方法STATMIX。使用两个神经网络体系结构，在CIFAR-10和CIFAR-100上经验测试了STATMIX。在所有FL实验中，与基线训练相比，STATMIX的应用都提高了平均准确性（不使用Statmix）。在非FL设置中也可以观察到一些改进。
Availability of large amount of annotated data is one of the pillars of deep learning success. Although numerous big datasets have been made available for research, this is often not the case in real life applications (e.g. companies are not able to share data due to GDPR or concerns related to intellectual property rights protection). Federated learning (FL) is a potential solution to this problem, as it enables training a global model on data scattered across multiple nodes, without sharing local data itself. However, even FL methods pose a threat to data privacy, if not handled properly. Therefore, we propose StatMix, an augmentation approach that uses image statistics, to improve results of FL scenario(s). StatMix is empirically tested on CIFAR-10 and CIFAR-100, using two neural network architectures. In all FL experiments, application of StatMix improves the average accuracy, compared to the baseline training (with no use of StatMix). Some improvement can also be observed in non-FL setups.
