[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125916-en":3,"doc-seo-125916-105":31,"detail-sidebar-cat-0-en-105":93},{"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},125916,2336474459895,"Aria","https://ap-avatar.wpscdn.com/avatar/22000baeef7a5ed0655?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786071322749376916",8,"Research & Report","Heterogeneity - An Open Challenge for Federated On-board Machine Learning","The document addresses heterogeneity as a key open challenge for federated learning in orbital edge computing with on-board machine learning on satellites. It motivates the shift from monolithic spacecraft to distributed small-satellite missions and highlights communication bottlenecks. While prior work targets homogeneous constellations, it focuses on cross-provider ad-hoc collaborations and systematically reviews challenges for this scenario, outlining state of the art, connections across application and theory, and a gap analysis.","Heterogeneity: An Open Challenge for Federated On-board  \nMachine Learning  \nMaria Hartmann∗1, Grégoire Danoy 1,2 , Pascal Bouvry2  \n1 SnT, University of Luxembourg, Luxembourg  \n2 FSTM, University of Luxembourg, Luxembourg  \nThe design of satellite missions is currently undergoing a paradigm shift from the historical approach of individualised monolithic satellites towards distributed mission configurations, consisting of multiple small satellites. With a rapidly growing number of such satellitesnow deployed in orbit, each collecting large amounts of data, interest in on-board orbital edge computing is rising. Federated Learning is a promising distributed computing approach in this context, allowing multiple satellites to collaborate efficiently in training on-board machine learning models. Though recent works on the use of Federated Learning in orbital edge computing have focused largely on homogeneous satellite constellations, Federated Learning could also be employed to allow heterogeneous satellites to form ad-hoc collaborations, [e.g. in](e.g. in)[ ](e.g. in)the case of communications satellites operated by different providers. Such an application presents additional challenges to the Federated Learning paradigm, arising largely from the heterogeneity of such a system. In this position paper, we offer a systematic review of these challenges in the context of the cross-provider use case, giving a brief overview of the state-of-the-art for each, and providing an entry point for deeper exploration of each issue.  \n1 Introduction  \nWith advances in hardware and software capabilities, distributed satellite mission configurations are progressively replacing the classical paradigm of using a single monolithic spacecraft. With nanosatellites able to generate and store increasingly large amounts of data through various on-board sensors, downlink capacity is becoming a major bottleneck in processing the gathered information. To manage this problem, there is an ongoing drive towards shifting data processing onto satellites[1] – this strategy is referred to as Orbital Edge Computing (OEC)[2] . The overarching idea of OEC is to leverage on-board computing capabilities of each satellite to process locally gathered data, reducing the size and amount of required trans-  \n∗ [Corresponding author. E-Mail: {firstname.lastname}@uni.lu](Corresponding author. E-Mail: {firstname.lastname}@uni.lu)  \nmissions and speeding up evaluation. A promising variant of OEC proposes deploying Federated Learning [3](FL) on satellites, allowing the joint training of on-board machine learning models across the data gathered by multiple satellites with a limited communication budget [4] . Under a FL scheme, each satellite performs on-board machine learning on the data it collects, training a local model – see Figure 1 . These models are shared periodically among participants, allowing them to be aggregated into a more accurate global model on which to continue training. Aggregation can take place with the aid of a parameter server on the ground or in orbit, or in a fully decentralised manner between satellites. Fundamental advantages of this approach include a vastly reduced communication cost compared to the transmission of raw data, and the inherent privacy advantages of compartmentalising data on satellites.  \nCurrent literature on the use of Federated Learning in Orbital Edge Computing is focused primarily on a single use case: using Federated Learning in a single, dedicated constellation of satellites. However, another frequently occurring scenario appears largely unstudied: the potential for satellites from different missions and providers to form (ad-hoc) cross-provider collaborations. In this position paper, we offer an initial exploration of the conceptual challenges associated with this use case: we identify the characteristics of the problem, present a brief survey of the state of the art for each, connecting existing research from the application d","cbCailw69aYBOAfN","https://ap.wps.com/l/cbCailw69aYBOAfN","pdf",1689274,7,1,6,"English","en",105,"# Introduction\n## Orbital edge computing and federated learning\n# Survey results\n## Orbital edge computing and federated learning","[{\"question\":\"What problem does the document highlight for satellite federated learning?\",\"answer\":\"It highlights system heterogeneity as a central open challenge when satellites from different missions and providers collaborate ad-hoc through federated learning.\"},{\"question\":\"Why is orbital edge computing important in the document’s context?\",\"answer\":\"It moves data processing onto satellites to reduce the amount and size of data that must be downlinked, alleviating downlink capacity bottlenecks and speeding evaluation.\"},{\"question\":\"How does federated learning work among satellites in the described scheme?\",\"answer\":\"Each satellite trains a local on-board model on its collected data, periodically shares model updates, aggregates them into a global model (via a server or decentralized), and continues training with the updated model.\"}]","Heterogeneity - An Open Challenge for Federated On-board Machine Learning | PDF",1785902018,15,{"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":88,"head_meta":90,"extra_data":92,"updated_unix":29},"heterogeneity-an-open-challenge-for-federated-on-board-machine-learning","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"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":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/heterogeneity-an-open-challenge-for-federated-on-board-machine-learning/125916/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-26","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What problem does the document highlight for satellite federated learning?","Question",{"text":77,"@type":78},"It highlights system heterogeneity as a central open challenge when satellites from different missions and providers collaborate ad-hoc through federated learning.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"Why is orbital edge computing important in the document’s context?",{"text":82,"@type":78},"It moves data processing onto satellites to reduce the amount and size of data that must be downlinked, alleviating downlink capacity bottlenecks and speeding evaluation.",{"name":84,"@type":75,"acceptedAnswer":85},"How does federated learning work among satellites in the described scheme?",{"text":86,"@type":78},"Each satellite trains a local on-board model on its collected data, periodically shares model updates, aggregates them into a global model (via a server or decentralized), and continues training with the updated model.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,112,116,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":108,"doc_module":4,"doc_module_name":47,"category_name":109,"show_sort_weight":110,"slug":111},5,"Comic",60,"comic",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":108,"slug":138},19,"General","general"]