Federated Learning 里面一个的一个 Open Problem 是，如果每个 local device 上面的数据，是非常 biased...
In this section, we introduce the details of our communication-efficient federated learning approach based on knowledge distillation (FedKD). We first present a definition of the problem studied in this paper, then introduce the details of our approach, and finally present some discussions on the ...
Federated Learning (FL) 的名字应该最早由Google在2016年的时候提出来的. 按照Google的说法, 最早是用在Gboard上的, 主要还是为了保护用户的隐私数据, 现在也用在很多Google自己的App上. 但是FL的概念其实很早就有了, 其核心就是一个分布式的机器学习, 像Virginia Smith在Berkeley的时候就已经开始做相关的研究了, ...
In this paper, we explore federated learning (FL) as a collaborative learning paradigm, in which models can be trained across several institutions without explicitly sharing patient data. We study the impact of data distribution on the performance of FL, i.e., when hospitals have more or less...
Federated learning emerges as an efficient approach to exploit distributed data and computing resources, so as to collaboratively train machine learning models. At the same time, federated learning obeys the laws and regulations and ensures data security and data privacy. In this paper, we provide ...
Compared to existing distributed learning schemes, FL is distinguished with several key aspects, explained in Google's paper about FL [147] as follows: • Data are heterogeneous and must be assumed to be non-identical, independent (none-iid). Training the data on a given user is typically ...
Federated learning (FL) is a promising framework for distributed machine learning that trains models without sharing local data while protecting privacy. F
In this paper, we adapted a master-server architecture, where each client node, representing each medical institution, locally utilizes the same deep learning architecture as one another and the global model, which we assume to be hosted on a central server hub. Each institution trains its ...
看过Google的Towards Federated Learning System Design那篇paper的同学都知道FL是一个需要多节点synchronize(进行模型聚合)的过程,然而多节点协同还是比较难的。体现在以下两点: 通信异构:不同节点的带宽有限,而且异构(2G/4G/5G/WiFi/…)。 计算异构:不同节点算力不一样。
（1）横向联邦学习。横向联邦学习又称为特征对齐的联邦学习（Feature-Aligned Federated Learning），是把...