Federated learning is a distributed machine learning framework which enables different parties to collaboratively train a model while protecting data privacy and security. Due to model complexity, network unreliability and connection in-stability, communication cost has became a major bottleneck for applying federated learning to real-world applications. Current existing strategies are either need to manual setting for hyperparameters, or break up the original process into multiple steps, which make it hard to realize end-to-end implementation. In this paper, we propose a novel compression strategy called Residual Pooling Network (RPN). Our experiments show that RPN not only reduce data transmission effectively, but also achieve almost the same performance as compared to standard federated learning. Our new approach performs as an end-to-end procedure, which should be readily applied to all CNN-based model training scenarios for improvement of communication efficiency, and hence make it easy to deploy in real-world application without much human intervention.
IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；Center for Computational Health（计算健康中心）
In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited. We develop a Bayesian nonparametric framework for federated learning with neural networks. Each data server is assumed to provide local neural network weights, which are modeled through our framework. We then develop an inference approach that allows us to synthesize a more expressive global network without additional supervision, data pooling and with as few as a single communication round. We then demonstrate the efficacy of our approach on federated lea…
Recent Methodological Advances in Federated Learning for Healthcare
University of Cambridge（剑桥大学）；University of Bremen（不来梅大学）；University of Helsinki（赫尔辛基大学）；Addenbrooke’s Hospital, Cambridge University Hospitals NHS Trust（剑桥大学医院NHS信托基金会阿登布鲁克医院）
Department of Computer, Control and Management Engineering, Sapienza University of Rome（罗马萨皮恩扎大学计算机、控制与管理工程系）；Department of Computer Science, Sapienza University of Rome（罗马萨皮恩扎大学计算机科学系）；Università della Svizzera Italiana（意大利瑞士大学）
Purdue University（普渡大学）；University at Buffalo–SUNY（纽约州立大学布法罗分校）
Federated learning (FL) has been promoted as a popular technique for training machine learning (ML) models over edge/fog networks. Traditional implementations of FL have largely neglected the potential for inter-network cooperation, treating edge/fog devices and other infrastructure participating in ML as separate processing elements. Consequently, FL has been vulnerable to several dimensions of network heterogeneity, such as varying computation capabilities, communication resources, data qualities, and privacy demands. We advocate for cooperative federated learning (CFL), a cooperative edge/f…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Purdue University（普渡大学）；University at Buffalo (SUNY)（纽约州立大学布法罗分校）；Duke University（杜克大学）
We investigate training machine learning (ML) models across a set of geo-distributed, resource-constrained clusters of devices through unmanned aerial vehicles (UAV) swarms. The presence of time-varying data heterogeneity and computational resource inadequacy among device clusters motivate four key parts of our methodology: (i) stratified UAV swarms of leader, worker, and coordinator UAVs, (ii) hierarchical nested personalized federated learning (HN-PFL), a distributed ML framework for personalized model training across the worker-leader-core network hierarchy, (iii) cooperative UAV resource p…
Differentially private federated learning with Byzantine-robust aggregation: A cross-domain framework for secure model training in banking and healthcare systems
Protocol Choices Matter More Than the Aggregation Algorithm: Federated Learning for In-Hospital Mortality Prediction in Care-Unit and Multi-Hospital Federations
Instituto Federal de Educação, Ciência e Tecnologia do Rio Grande do Norte (IFRN)（北大河州教育、科学和技术联邦学院（IFRN））
FedECA: Federated External Control Arms for Causal Inference with Time-To-Event Data in Distributed Settings
Owkin, Inc.（Owkin公司）；Georges Pompidou European Hospital（乔治·蓬皮杜欧洲医院）；AP-HP（巴黎公立医院集团）；Centre de Recherche des Cordeliers（科尔得利研究中心）；Inserm（法国国家健康与医学研究院）；Institut du Cancer Paris CARPEM（巴黎CARPEM癌症研究所）；AP-HP Centre（巴黎公立医院集团中心）；Sorbonne University（索邦大学）；Centre de Recherche sur l’Inflammation (CRI)（炎症研究中心）；CNRS（法国国家科学研究中心）；Beaujon Hospital（博容医院）；Catalan Institute of Oncology（加泰罗尼亚肿瘤研究所）；Doctor Josep Trueta University Hospital（约瑟普·特鲁埃塔大学医院）；Pancreatic Cancer Action Network（胰腺癌行动网络）
University of California San Diego（加州大学圣地亚哥分校）；Rutgers University（罗格斯大学）
Neural architecture search, which aims to automatically search for architectures (e.g., convolution, max pooling) of neural networks that maximize validation performance, has achieved remarkable progress recently. In many application scenarios, several parties would like to collaboratively search for a shared neural architecture by leveraging data from all parties. However, due to privacy concerns, no party wants its data to be seen by other parties. To address this problem, we propose federated neural architecture search (FNAS), where different parties collectively search for a differentiable…
FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data
Institute for Predictive Deep Learning in Medicine and Healthcare（预测医学与健康人工智能研究所）；Justus Liebig University Gießen（吉森约瑟夫·李比希大学）；Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心 (hessian.AI)）；Department of Medical Informatics（医学信息学系）；University Medical Center Göttingen（哥廷根大学医学中心）；Max Planck Institute for Biology of Ageing（马克斯·普朗克衰老生物学研究所）
University of Turin（都灵大学）；Leonardo S.p.A.（莱昂纳多股份公司）
Training Deep Learning (DL) models require large, high-quality datasets, often assembled with data from different institutions. Federated Learning (FL) has been emerging as a method for privacy-preserving pooling of datasets employing collaborative training from different institutions by iteratively globally aggregating locally trained models. One critical performance challenge of FL is operating on datasets not independently and identically distributed (non-IID) among the federation participants. Even though this fragility cannot be eliminated, it can be debunked by a suitable optimization of…
Imperial College London（帝国理工学院）；University of Bayreuth（拜罗伊特大学）
Deep learning has been successful in BCI decoding. However, it is very data-hungry and requires pooling data from multiple sources. EEG data from various sources decrease the decoding performance due to negative transfer. Recently, transfer learning for EEG decoding has been suggested as a remedy and become subject to recent BCI competitions (e.g. BEETL), but there are two complications in combining data from many subjects. First, privacy is not protected as highly personal brain data needs to be shared (and copied across increasingly tight information governance boundaries). Moreover, BCI dat…
Privacy-Preserving Multi-Center Differential Protein Abundance Analysis with FedProt
Technical University of Munich（慕尼黑工业大学）；University of Hamburg（汉堡大学）；Helmholtz Center Munich（慕尼黑亥姆霍兹中心）；LMU Munich（慕尼黑大学）；Max Planck Institute of Biochemistry（马克斯·普朗克生物化学研究所）；German Center for Neurodegenerative Diseases (DZNE)（德国神经退行性疾病中心）；Fraunhofer Institute for Cell Therapy and Immunology IZI（弗劳恩霍夫细胞治疗与免疫学研究所）；University of Applied Science Coburg（科堡应用科学大学）；University Hospital Erlangen（埃尔朗根大学医院）；Leiden University Medical Center（莱顿大学医学中心）；University of Greifswald（格赖夫斯瓦尔德大学）；German Center for Cardiovascular Diseases (DZHK)（德国心血管疾病中心）；University of Southern Denmark（南丹麦大学）；Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）；Klinikum rechts der Isar（慕尼黑伊萨尔河右岸医院）；Munich Cluster for Systems Neurology (SyNergy)（慕尼黑系统神经学集群）
Federated Few-Shot Learning for Epileptic Seizure Detection Under Privacy Constraints
Pro2Future GmbH（Pro2Future公司）；Institute for Machine Learning（机器学习研究所）；Johannes Kepler University（约瑟夫·约瑟夫·凯普勒大学）；Institute of Pervasive Computing（普及计算研究所）
