论文标题
迈向联邦学习的数据异质性
Toward Data Heterogeneity of Federated Learning
论文作者
论文摘要
联合学习是机器学习的流行范式。理想情况下，当所有客户共享类似的数据分布时，联合学习效果最好。但是，在现实世界中并不总是这样。因此，从学术界和行业中，联邦学习的联合学习主题越来越多。在这个项目中，我们首先进行了广泛的实验，以说明数据偏斜和数量偏斜将如何影响最新的联合学习算法的性能。然后，我们提出了一种新的算法FEDMIX，该算法调整了现有的联合学习算法，并显示了其性能。我们发现，诸如FEDPROX和FEDNOVA等现有的最新算法在所有测试案例中均未有显着改善。但是，通过测试现有的和新算法，调整客户端似乎比调整服务器端更有效。
Federated learning is a popular paradigm for machine learning. Ideally, federated learning works best when all clients share a similar data distribution. However, it is not always the case in the real world. Therefore, the topic of federated learning on heterogeneous data has gained more and more effort from both academia and industry. In this project, we first do extensive experiments to show how data skew and quantity skew will affect the performance of state-of-art federated learning algorithms. Then we propose a new algorithm FedMix which adjusts existing federated learning algorithms and we show its performance. We find that existing state-of-art algorithms such as FedProx and FedNova do not have a significant improvement in all testing cases. But by testing the existing and new algorithms, it seems that tweaking the client side is more effective than tweaking the server side.
