Comparative assessment of federated and centralized machine learning
Samsung R&D Institute India – Bangalore（三星印度研发研究院 - 班加罗尔）；Birla Institute of Technology and Science（比尔拉理工学院）；Indian Statistical Institute（印度统计研究所）；Samsung Electronics（三星电子）
Ibrahim Abdul Majeed, Sagar Kaushik, Aniruddha Bardhan, Venkata Siva Kumar Tadi, Hwang-Ki Min, Karthikeyan Kumaraguru, Rajasekhara Duvvuru Muni
Federated Learning (FL) is a privacy preserving machine learning scheme, where training happens with data federated across devices and not leaving them to sustain user privacy. This is ensured by making the untrained or partially trained models to reach directly the individual devices and getting locally trained "on-device" using the device owned data, and the server aggregating all the partially trained model learnings to update a global model. Although almost all the model learning schemes in the federated learning setup use gradient descent, there are certain characteristic differences brought about by the non-IID nature of the data availability, that affects the training in comparison to the centralized schemes. In this paper, we discuss the various factors that affect the federated learning training, because of the non-IID distributed nature of the data, as well as the inherent differences in the federating learning approach as against the typical centralized gradient descent techniques. We empirically demonstrate the effect of number of samples per device and the distribution of output labels on federated learning. In addition to the privacy advantage we seek through federated learning, we also study if there is a cost advantage while using federated learning frameworks. We show that federated learning does have an advantage in cost when the model sizes to be trained are not reasonably large. All in all, we present the need for careful design of model for both performance and cost.
GC-Fed: Gradient Centralized Federated Learning with Partial Client Participation
Department of Electrical Engineering and Computer Science, University of Stavanger（电子工程与计算机科学系，斯瓦尔内尔大学）；Department of Software, Sookmyung Women's University（软件系，淑明女子大学）；Department of Electrical and Information Engineering, Seoul National University of Science and Technology（电子与信息工程系，首尔科学技术大学）
Federated Learning Architectures: A Performance Evaluation with Crop Yield Prediction Application
Department of Computer Science Mahishadal Raj College, Mahishadal, West Bengal, 721628, India；Distributed Systems (CLOUDS) Laboratory, \ of Computing；Information Systems, The University of Melbourne, Victoria, 3052, Australia
dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis
School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；PKU-OCTA Laboratory for Blockchain and Privacy Computing（区块链与隐私计算实验室）；National Engineering Research Center for Software Engineering, Peking University（软件工程国家工程研究中心）；State University of New York at Buffalo（纽约州立大学布法罗分校）
Reducing bias and increasing utility by federated generative modeling of medical images using a centralized adversary
University of British Columbia（不列颠哥伦比亚大学）；Microsoft（微软）
我们介绍了FELICIA（FEDERATED LEARNING WITH A CentralIzed Advertisement），一种支持协作学习的生成机制。特别是，我们展示了数据有限和有偏见的数据所有者如何从其他数据所有者那里受益，同时保持所有来源的数据的私密性。这是医学图像分析中的常见情况，其中隐私立法阻止数据在本地场所之外共享。FELICIA适用于生成对抗网络（GAN）架构的大家族，包括香草和条件GANs，如本工作所示。我们表明，通过使用FELICIA机制，有限的图像样本的数据所有者可以生成高质量的合成图像，具有高实用性，而数据所有者都没有提供访问其数据。共享仅通过一个中央数据库进行，该数据库只能访问合成数据。在这里，效用被定义为在真实测试集上的分类性能。我们使用基准图像数据集（MNIST，CIFAR-10）以及皮肤病变分类任务的医学图像上的几个现实的医疗保健系统上证明了这些好处。通过多个实验，我们表明，即使在最坏的情况下，将FELICIA与真实数据相结合，也能优雅地实现与真实数据相当的性能，而大多数结果显着提高了效用。
Better Methods and Theory for Federated Learning: Compression, Client Selection and Heterogeneity
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
联邦学习（FL）是涉及多个客户端的新兴机器学习范例，例如，移动电话设备，具有协作解决由中央服务器协调的机器学习问题的激励。FL是由Konečnet al.和McMahan et al.在2016年提出的，作为传统集中式机器学习的一种可行的隐私保护替代方案，因为通过构造，训练数据点是分散的，并且永远不会由客户端传输到中央服务器。因此，FL在一定程度上减轻了与集中式数据汇集相关的隐私风险。不幸的是，FL的优化面临着集中式优化通常不需要处理的几个特定问题。在这篇论文中，我们确定了这些挑战中的一些，并提出了新的方法和算法来解决这些问题，最终目标是使实际的FL解决方案支持数学上严格的保证。
Exploring Federated Learning for Thermal Urban Feature Segmentation -- A Comparison of Centralized and Decentralized Approaches
Scientific Computing Center (SCC), Karlsruhe Institute of Technology (KIT)（科学计算中心（SCC），卡尔斯鲁厄理工学院（KIT））；Institute for Industrial Production (IIP), Karlsruhe Institute of Technology (KIT)（工业生产研究所（IIP），卡尔斯鲁厄理工学院（KIT））；Instituto de Física de Cantabria (IFCA), CSIC-UC（坎塔布里物理研究所（IFCA），CSIC-UC）
FLAM: Evaluating Model Performance with Aggregatable Measures in Federated Learning
Institute of Data-Centric Software Systems (IDSS)（数据导向软件系统研究所）；Hochschule Karlsruhe（卡尔斯鲁厄应用科学大学）；Scalable Software Systems Research Group（可扩展软件系统研究组）；TU Berlin（柏林技术大学）
Principled Federated Random Forests for Heterogeneous Data
Inria（法国国家信息与自动化研究所）；PreMeDICaL（预医学实验室）；Inserm（法国国家医学研究院）；University of Montpellier（蒙彼利埃大学）；Sorbonne Université（索邦大学）；Université Paris Cité（巴黎城市大学）；CNRS（国家科学研究中心）；LPSM（巴黎高等师范学院）
Privacy-preserving federated prediction of pain intensity change based on multi-center survey data
University of Hamburg（汉堡大学）；University Medical Center Hamburg-Eppendorf（汉堡-埃彭多夫大学医学中心）；University of Southern Denmark（南丹麦大学）；Næstved-Slagelse-Ringsted Hospitals（奈斯特韦兹-斯拉厄尔瑟-灵斯泰兹医院）
Towards Sparsified Federated Neuroimaging Models via Weight Pruning
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；Stevens Neuroimaging and Informatics Institute, University of Southern California（南加州大学史蒂文斯神经影像与信息学研究所）
