[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128402-en":3,"doc-seo-128402-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128402,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","Interaction-Aware Gaussian Weighting for Clustered Federated Learning - read online free","Federated Learning preserves privacy while enabling decentralized model training, yet conventional FL suffers when clients hold heterogeneous data and imbalanced classes, harming accuracy and stability. Clustered FL improves personalization by grouping clients with similar data distributions, reducing the negative effect of heterogeneity under privacy constraints. This work introduces FedGWC (Federated Gaussian Weighting Clustering), which forms homogeneous clusters by mapping empirical client losses to interactions via a Gaussian reward mechanism and evaluates cohesion using the Wasserstein Adjusted Score.","POLITECNICO DI TORINO Repository ISTITUZIONALE  \nInteraction-Aware Gaussian Weighting for Clustered Federated Learning  \nOriginal  \nInteraction-Aware Gaussian Weighting for Clustered Federated Learning / Licciardi, Alessandro; Leo, Davide; Fanì, Eros; Caputo, Barbara; Ciccone, Marco. -ELETTRONICO. -267:(2025), pp. 1-25. ( 42nd International Conference on Machine Learning (ICML 2025) Vancouver (Canada) 13/07/2025-19/07/2025) .  \nAvailability:  \nThis version is available at: 11583/3003711 since: 2025-11-21T23:23:39Z  \nPublisher: PMLR  \nPublished DOI:  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \n(Article begins on next page)  \n21 February 2026  \nInteraction-Aware Gaussian Weighting for Clustered Federated Learning  \nAlessandro Licciardi * 1 2 Davide Leo * 3 Eros Fan3 4 Barbara Caputo 3 Marco Ciccone † 5  \nAbstract  \nFederated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustered FL method, FedGWC (Federated Gaussian Weighting Clustering), which groups clients based on their data distribution, allowing training of a more robust and personalized model on the identified clusters. FedGWC identifies homogeneous clusters by transforming individual empirical losses to model client interactions with a Gaussian reward mechanism. Additionally, we introduce the Wasserstein Adjusted Score, a new clustering metric for FL to evaluate cluster cohesion with respect to the individual class distribution. Our experiments on benchmark datasets show that FedGWC outperforms existing FL algorithms in cluster quality and classification accuracy, validating the efficacy of our approach. Code is available at [https:](https:)//[github.com/davedleo/FedGWC](github.com/davedleo/FedGWC)  \n1. Introduction  \nFederated Learning (FL) (McMahan et al., 2017) has emerged as a promising paradigm for training models on decentralized data while preserving privacy. Unlike tradi-  \n*Equal contribution 1Department of Mathematical Sciences, Polytechnic University of Turin, Italy 2Istituto Nazionale di Fisica Nucleare (INFN), Sezione di Torino, Turin, Italy 3Department of Computing and Control Engineering, Polytechnic University of Turin, Italy 4Basque Center for Applied Mathematics (BCAM), Bilbao, Spain 5Vector Institute, Toronto, Ontario, Canada. † Work started when the author was at the Polytechnic University of Turin. Correspondence to: Alessandro Licciardi \u003Calessandro.licciardi@polito.it> .  \nProceedings of the 42 nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025 . Copyright 2025 by the author(s) .  \ntional machine learning frameworks, FL enables collaborative training between multiple clients without requiring data transfer, making it particularly attractive in privacy-sensitive domains (Bonawitz et al., 2019) . FL was introduced primarily to address two major challenges in decentralized scenarios: ensuring privacy (Kairouz et al., 2021) and reducing communication overhead (Hamer et al., 2020 ; Asad et al., 2020) . In particular, FL algorithms must guarantee communication efficiency, to reduce the burden associated with the exchange of model updates between clients and the central server, while maintaining privacy, as clients should not expose their private data during the training process.  \nA core challenge in federated learning is data heterogeneity (Li et al., 2020) . This manifests in two key ways: through imbalances in data quantity and class distrib","cbCaifSSVu5VNaNi","https://ap.wps.com/l/cbCaifSSVu5VNaNi","pdf",958230,3,1,26,"English","en",105,"# Introduction\n## Challenges in federated learning\n## Proposed clustered approach (FedGWC)\n## Clustering via Gaussian reward mechanism\n## Wasserstein Adjusted Score","[{\"question\":\"What problem does FedGWC address in federated learning?\",\"answer\":\"FedGWC targets data heterogeneity and class imbalance, which degrade performance and can cause unstable convergence in conventional federated learning.\"},{\"question\":\"How does FedGWC form clusters of clients?\",\"answer\":\"FedGWC groups clients by similar data distributions inferred from their empirical loss functions, using a Gaussian reward mechanism to model client interactions.\"},{\"question\":\"What is the Wasserstein Adjusted Score used for?\",\"answer\":\"It is a new clustering metric for FL that evaluates cluster cohesion with respect to the individual class distribution, helping assess how well clients are grouped.\"}]","Interaction-Aware Gaussian Weighting for Clustered Federated Learning - read online free | PDF",1785947310,66,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"interaction-aware-gaussian-weighting-for-clustered-federated-learning-read-online-free","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/interaction-aware-gaussian-weighting-for-clustered-federated-learning-read-online-free/128402/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-28","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does FedGWC address in federated learning?","Question",{"text":76,"@type":77},"FedGWC targets data heterogeneity and class imbalance, which degrade performance and can cause unstable convergence in conventional federated learning.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does FedGWC form clusters of clients?",{"text":81,"@type":77},"FedGWC groups clients by similar data distributions inferred from their empirical loss functions, using a Gaussian reward mechanism to model client interactions.",{"name":83,"@type":74,"acceptedAnswer":84},"What is the Wasserstein Adjusted Score used for?",{"text":85,"@type":77},"It is a new clustering metric for FL that evaluates cluster cohesion with respect to the individual class distribution, helping assess how well clients are grouped.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]