[论文阅读] 联邦学习在医疗领域的应用综述 Federated Learning for Healthcare Infomatics

联邦学习在医疗领域的应用综述 Federated Learning for Healthcare Infomatics

本文主要讲的是联邦学习在医疗领域的应用。作者的背景可能更多的是医学，所以本文比较简单，对联邦学习的入门者阅读没有障碍。
🙋‍♂️ 张同学 zhangruiyuan@zju.edu.cn， 有问题请联系我

〇、作者背景信息

通信作者：Fei Wang 康奈尔大学医学部 威尔康奈尔医学院的副教授

一 、Introduction

大量的医学数据来源于：clinical institution, patient individuals, insurance companies, and pharmaceutical industries. 这为数据驱动的计算机技术带来了机会。但有这样的问题 **“For example, different hospitals may be able to access the clinical records of their own patient populations only。 这些数据受到了HIPAA的保护。这为深度学习等带来了问题。”**联邦学习的出现为解决这个问题，联邦学习避免了收集数据带来的问题。

Tips 联邦学习的起源：The term “federated learning” is not new. In 1976, Patrick Hill, a philosophy professor, first developed the Federated Learning Community (FLC) to bring people together to jointly learn, which helped students overcome the anonymity and isolation in large research universities [42]. Subsequently, there were several efforts aiming at building federations of learning content and content repositories [6, 74, 83]. In 2005, Rehak et al. [83] developed a reference model describing how to establish an inter- operable repository infrastructure by creating federations of repositories, where the metadata are collected from the contributing repositories into a central registry pro- vided with a single point of discovery and access. The ultimate goal of this model is to enable learning from diverse content repositories. These practices in federated learning community or federated search service have provided effective references for the development of federated learning algorithms.

联邦学习在医学领域有比较大的前景。
building a model for predicting the hospital readmission risk with patient Electronic Health Records (EHR) [71]
and consumer (patient)-based appli- cations (e.g., screening atrial fibrillation with electrocardiograms captured by smart- watch [79]),

本文的贡献：

1. 总结联邦学习的主要挑战、最近进展
2. 通过最新的研究说明联邦学习在医疗领域的潜力
3. 最后，讨论未来机会和为解决的问题

其他联邦学习综述，下面的文章也是值得阅读的。

• Yang et al. [109] wrote the early federated learning survey summarizing the general privacy-preserving techniques that can be applied to federated learning.
• Some researchers surveyed sub-problems of federated learn- ing, e.g., personalization techniques [59], semi-supervised learning algorithms [49], threat models [68], and mobile edge networks [66].
• Kairouz et al. [51] discussed recent advances and presented an extensive collection of open problems and chal- lenges.
• Li et al. [63] conducted the review on federated learning from a system viewpoint.

二、Federated Learning

就是一个很普通的联邦学习介绍，

在联邦学习中可能用到的优化函数

介绍了本文作者认为的联邦学习挑战。

2.1 联邦学习的统计挑战

However, FedAvg does not address the statistical challenge of strongly skewed data distributions. The performance of convolutional neural networks trained with FedAvg algorithm can reduce significantly due to the weight divergence [111].

• Consensus Solution
• Pluralistic Solution

2.2 Communication Efficiency of Federated Learning

为了解决通信问题，以下是4种解决问题的办法。

2.3 隐私和安全

三、Application

本章从两个部分进行展开：healthcare部分和其他

3.1 healthcare

3.2 当前联邦学习框架

四、Conclusions and Open Questions

• Data Quality
• Incorporating Expert Knowledge 需要与专家知识结合
• 激励机制
• 个性化模型
• 要想在医院的场景下进行使用，需要更高的模型精度

其他

这篇文章给我的启发是，让我觉得我之前写的文章也并不是一无是处。