[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118520-en":3,"doc-seo-118520-105":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},118520,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Emerging trends in federated learning - from model fusion to federated X learning","Federated learning is a learning paradigm that separates data collection from model training through multi-party computation and model aggregation. It can flexibly integrate with other learning frameworks, enabling improvements over the vanilla federated averaging algorithm. The survey examines learning algorithms for better aggregation and reviews model fusion approaches including adaptive aggregation, regularization, clustered methods, and Bayesian techniques. It also discusses federated X learning spanning multitask, meta-, transfer, unsupervised, and reinforcement learning, highlighting challenges, applications, and future directions.","International Journal of Machine Learning and Cybernetics (2024) 15:3769–3790  \n[https://doi.org/10.1007/s13042-024-02119-1](https://doi.org/10.1007/s13042-024-02119-1)  \nEmerging trends in federated learning: from model fusion to federated X learning  \nShaoxiong Ji1 · Yue Tan2 · Teemu Saravirta1 · Zhiqin Yang4 · Yixin Liu5 · LauriVasankari3 · Shirui Pan6 · Guodong Long2 · Anwar Walid7,8  \nReceived: 24 November 2023 / Accepted: 25 February 2024 / Published online: 2 April 2024 © The Author(s) 2024  \nAbstract  \nFederated learning is a new learning paradigm that decouples data collection and model training via multi-party computation and model aggregation. As a flexible learning setting, federated learning has the potential to integrate with other learning frameworks. We conduct a focused survey of federated learning in conjunction with other learning algorithms. Specifically, we explore various learning algorithms to improve the vanilla federated averaging algorithm and review model fusion methods such as adaptive aggregation, regularization, clustered methods, and Bayesian methods. Following the emerging trends, we also discuss federated learning in the intersection with other learning paradigms, termed federated X learning, where X includes multitask learning, meta-learning, transfer learning, unsupervised learning, and reinforcement learning. In addition to reviewing state-of-the-art studies, this paper also identifies key challenges and applications in this field, while also highlighting promising future directions.  \nKeywords Federated learning · Model fusion · Learning algorithms  \n1 Introduction  \nVast quantities of data are required for state-of-the-art machine learning algorithms. However, the data cannot be uploaded to a central server or cloud due to sheer volume, privacy, or legislative reasons. Federated learning (FL) [1], also known as collaborative learning, has been the subject of many studies. FL adopts a distributed machine learning architecture with a central server for model aggregation,  \nwhere clients themselves update the machine learning model. Clients can maintain ownership of their data, i.e. , upload only the updated model to the central server and not expose any of their private data.  \nThe federated learning paradigm addresses several challenges. The first challenge is privacy. Local data ownership inherits a basic level of privacy. However, federated learning systems can be vulnerable to adversarial attacks, such as backdoor attack [2], model poisoning [3], and data  \n* Shaoxiong Ji [shaoxiong.ji@helsinki.fi](shaoxiong.ji@helsinki.fi)  \n* Yixin Liu [yixin.liu@monash.edu](yixin.liu@monash.edu)  \nYue Tan [yue.tan@student.uts.edu.au](yue.tan@student.uts.edu.au)[ ](yue.tan@student.uts.edu.au)Teemu Saravirta [teemu.saravirta@helsinki.fi](teemu.saravirta@helsinki.fi)  \nZhiqin Yang  \n[yangzqccc@buaa.edu.cn](yangzqccc@buaa.edu.cn)[ ](yangzqccc@buaa.edu.cn)Lauri Vasankari [lauri.vasankari@aalto.fi](lauri.vasankari@aalto.fi)  \nShirui Pan  \n[s.pan@griffith.edu.au](s.pan@griffith.edu.au)  \nGuodong Long  \n[guodong.long@uts.edu.au](guodong.long@uts.edu.au)  \nAnwar Walid  \n[aie13@columbia.edu](aie13@columbia.edu)  \n1 University of Helsinki, Helsinki, Finland  \n2 University of Technology Sydney, Ultimo, Australia  \n3 Aalto University, Espoo, Finland  \n4 Beihang University, Beijing, China  \n5 Monash University, Melbourne, Australia  \n6 Griffith University, Gold Coast, Australia  \n7 Amazon, New York, USA  \n8 Columbia University, New York, USA  \npoisoning [4] . The second challenge is the communication cost for model uploading and downloading. Improving communication efficiency is a critical issue [5–7] . Centralized network architecture also makes the central server suffer from a heavy communication workload, calling for a decentralized server architecture [8] . The third challenge is statistical heterogeneity. Aggregating clients’ models together can result in a non-optimal combined model as client data is often no","cbCair7XMA4vvTBn","https://ap.wps.com/l/cbCair7XMA4vvTBn","pdf",1108668,1,22,"English","en",105,"# Introduction\n## Privacy, communication cost, and statistical heterogeneity\n## Model aggregation methods and fairness\n## Label scarcity and learning paradigms\n# Federated X learning intersections\n## Multitask learning\n## Meta-learning and transfer learning\n## Unsupervised learning and reinforcement learning","[{\"question\":\"What problems does federated learning aim to address?\",\"answer\":\"It targets privacy concerns, communication costs between clients and a central server, and statistical heterogeneity caused by non-IID client data.\"},{\"question\":\"How do recent studies improve the vanilla federated averaging algorithm?\",\"answer\":\"They propose improved aggregation and learning algorithms, including adaptive weighting, attentive aggregation, regularization, clustering, and Bayesian approaches.\"},{\"question\":\"What does the paper mean by federated X learning?\",\"answer\":\"Federated X learning refers to federated learning combined with other paradigms where X includes multitask learning, meta-learning, transfer learning, unsupervised learning, and reinforcement learning.\"}]","Emerging trends in federated learning - from model fusion to federated X learning | PDF",1785683970,55,{"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},"emerging-trends-in-federated-learning-from-model-fusion-to-federated-x-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/emerging-trends-in-federated-learning-from-model-fusion-to-federated-x-learning/118520/",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","2026-08-02",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 problems does federated learning aim to address?","Question",{"text":75,"@type":76},"It targets privacy concerns, communication costs between clients and a central server, and statistical heterogeneity caused by non-IID client data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do recent studies improve the vanilla federated averaging algorithm?",{"text":80,"@type":76},"They propose improved aggregation and learning algorithms, including adaptive weighting, attentive aggregation, regularization, clustering, and Bayesian approaches.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the paper mean by federated X learning?",{"text":84,"@type":76},"Federated X learning refers to federated learning combined with other paradigms where X includes multitask learning, meta-learning, transfer learning, unsupervised learning, and reinforcement learning.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]