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...
The growing need for data privacy and security in machine learning has led to exploring novel approaches like federated learning (FL) that allow collaborative training on distributed datasets, offering a decentralized alternative to traditional data coll
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, ...
A Correction to this paper has been published: https://doi.org/10.1038/s41467-023-36188-7 References Mårtensson, G. et al. The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort study. Med. Image Anal. 66, 101714 (2020). Article Google Schola...
and application collaboration rely on the collaboration between edge PaaS and cloud PaaS. And service collaboration relies on the collaboration between the edge SaaS model and the cloud SaaS model. In this paper, we aim to explore the application and deployment of federated learning in the six typ...
Moreover, joining the user’s data with data from other users has some risks and this is mentioned in theGoogle researchpaper: Holding even an “anonymized” dataset can still put user privacy at risk via joins with other data. Here, the seminal paper on federated learning makes it clear ...
（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...
整篇文章思路还是比较清晰,但是在我看来稍微有几点遗憾。这个遗憾来自于作者的视角,作者还是以Google最开始的那篇paper的视角为出发点,也就是以2C的场景下横向联邦为出发点。 只展示了精度收到的影响,没有展示server通过梯度来推断原始数据。也就是安全问题。
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 ...
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...