[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119801-en":3,"doc-seo-119801-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119801,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","SoK - Assessing the State of Applied Federated Machine Learning","Federated Machine Learning (FedML) enables privacy-preserving model training by applying learning algorithms directly to distributed data without sharing raw records. Although FedML is supported by a strong theoretical framework, practical adoption remains limited, leaving an incomplete view of its real-world deployment. This systematic literature review analyzes 74 papers to characterize implementation patterns, emerging trends, motivational drivers, and application domains. It also synthesizes integration challenges, clarifying obstacles that hinder operationalization in privacy-critical environments.","SoK: Assessing the State of Applied Federated Machine Learning  \nTobias M¨uller1 , Maximilian Stbler2 , Hugo Gascn3 , Frank Kster2 and Florian Matthes 1  \n1 Technical University of Munich  \n2 German Aerospace Center (DLR)  \n3 German Edge Cloud (GEC)  \n{tobias.mueller1, [matthes](matthes}@tum.de)[}](matthes}@tum.de)[@tum.de](matthes}@tum.de), {maximilian.staebler, [frank.koester](frank.koester}@dlr.de)[}](frank.koester}@dlr.de)[@dlr.de](frank.koester}@dlr.de), [hugo.gascon@gec.io](hugo.gascon@gec.io)  \narXiv :2308 .02454v1 [ cs .LG] 3 Aug 2023  \nAbstract—Machine Learning (ML) has shown significant potential in various applications; however, its adoption in privacycritical domains has been limited due to concerns about data privacy. A promising solution to this issue is Federated Machine Learning (FedML), a model-to-data approach that prioritizes data privacy. By enabling ML algorithms to be applied directly to distributed data sources without sharing raw data, FedML offers enhanced privacy protections, making it suitable for privacycritical environments. Despite its theoretical benefits, FedML has not seen widespread practical implementation. This study aims to explore the current state of applied FedML and identify the challenges hindering its practical adoption. Through a comprehensive systematic literature review, we assess 74 relevant papers to analyze the real-world applicability of FedML. Our analysis focuses on the characteristics and emerging trends of FedML implementations, as well as the motivational drivers and application domains. We also discuss the encountered challenges in integrating FedML into real-life settings. By shedding light on the existing landscape and potential obstacles, this research contributes to the further development and implementation of FedML in privacy-critical scenarios.  \nIndex Terms—Federated Machine Learning, Collaborative Data Processing, Big Data, Systematization of Knowledge  \nI. INTRODUCTION  \nThe unprecedented growth of hyperscale computing has fuelled research in distributed architectures for training Machine Learning (ML) models at scale. Standard approaches require collecting large amounts of training data on a central server. These centralized platforms not only put the privacy of individual users at risk but also prevent cooperation between organizations due to the lack of trust in service providers [45] . At the same time, the realization that more training data is vital for improving the performance of predictive algorithms has created economic incentives to prioritize accumulating more personal and sensitive data. To address such increasing privacy concerns, McMahan et al. [36] introduced Federated Machine Learning (FedML), a novel ML paradigm that allows the training of a joint ML model on decentralized data without the need for direct data sharing. The model-to-data approach not merely increases privacy by design. Since the ML models are updated locally, the training and usage of these models can be performed without the need to communicate with a server. Additional to this offline usage, only gradients are  \nshared, which potentially reduces the communication load compared to centralized approaches, where whole datasets are exchanged. Despite its advantages and established theoretical framework, FedML is only sparsely adopted in real-world scenarios. This research aims to investigate the missing operationalization of FedML and disclose the challenges inhibiting a broad practical adoption. A growing literature corpus demonstrates the applicability of FedML in real-world scenarios, which provides detailed insights into the current state of applied FedML. By reviewing and systemizing this literature corpus on the described motivations, application domains, and experienced challenges, we aim to assess the current state of applied FedML. Finally, we intend to disclose the challenges inhibiting the broad practical adoption of FedML. Summarized, this systematic literature review ","cbCaijIrhCTFM8pu","https://ap.wps.com/l/cbCaijIrhCTFM8pu","pdf",1187347,1,9,"English","en",105,"# Introduction\n# Preliminaries\n## Federated learning workflow\n## Alternatives to client-server architectures","[{\"question\":\"What is the core idea of Federated Machine Learning (FedML) in this work?\",\"answer\":\"FedML trains a joint predictive model across decentralized parties without requiring direct data sharing. Each client computes local updates and sends gradients, while the server aggregates them.\"},{\"question\":\"How does the document assess the current state of applied FedML?\",\"answer\":\"It performs a comprehensive systematic literature review of 74 relevant papers and analyzes characteristics, trends, motivational drivers, application domains, and practical challenges.\"},{\"question\":\"Why is FedML difficult to adopt broadly in real-world settings?\",\"answer\":\"The paper discusses multiple challenges that inhibit practical operationalization and integration into real-life deployments, despite FedML’s theoretical advantages.\"}]","SoK - Assessing the State of Applied Federated Machine Learning | PDF",1785726379,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"sok-assessing-the-state-of-applied-federated-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/sok-assessing-the-state-of-applied-federated-machine-learning/119801/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the core idea of Federated Machine Learning (FedML) in this work?","Question",{"text":75,"@type":76},"FedML trains a joint predictive model across decentralized parties without requiring direct data sharing. Each client computes local updates and sends gradients, while the server aggregates them.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the document assess the current state of applied FedML?",{"text":80,"@type":76},"It performs a comprehensive systematic literature review of 74 relevant papers and analyzes characteristics, trends, motivational drivers, application domains, and practical challenges.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is FedML difficult to adopt broadly in real-world settings?",{"text":84,"@type":76},"The paper discusses multiple challenges that inhibit practical operationalization and integration into real-life deployments, despite FedML’s theoretical advantages.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]