[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126438-en":3,"doc-seo-126438-105":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},126438,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","Achieving Machine Learning Dependability Through Model Switching and Compression","Machine learning can be distributed to leverage more resources and protect privacy, yet existing work often evaluates only expected learning quality and ignores how learning quality is distributed. As a result, ML models may fail to deliver required performance in real-world mission-critical settings. This work introduces DepL, a framework for dependable learning orchestration that jointly decides data selection, model choice among full-size and compressed options, switching timing, and node cluster allocation, guaranteeing a target quality with specified probability while minimizing learning cost.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nAchieving Machine Learning Dependability Through Model Switching and Compression  \nOriginal  \nAchieving Machine Learning Dependability Through Model Switching and Compression / Malandrino, Francesco; Di Giacomo, Giuseppe; Levorato, Marco; Chiasserini, Carla Fabiana. -In: IEEE TRANSACTIONS ON MOBILE COMPUTING. -ISSN 1536-1233. - (2025) .  \nAvailability:  \nThis version is available at: 11583/3003642 since: 2025-10-05T17:25:26Z  \nPublisher: IEEE  \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  \nIEEE postprint/Author's Accepted Manuscript  \n©2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collecting works, for resale or lists, or reuse of any copyrighted component of this work in other works.  \n(Article begins on next page)  \n21 February 2026  \nAchieving Machine Learning Dependability Through Model Switching and Compression  \nFrancesco Malandrino, Senior Member, IEEE, Giuseppe Di Giacomo, Student Member, IEEE, Marco Levorato, Senior Member, IEEE, Carla Fabiana Chiasserini, Fellow, IEEE  \nAbstract—Machine learning (ML) can be often distributed, owing to the need to harness more resources and/or to preserve privacy. Accordingly, distributed learning has received significant attention from the literature; however, most works focus on the expected learning quality (e.g., loss) attained and do not consider the distribution thereof. It follows that ML models are not dependable, and may fall short of the required performance in many real-world cases. In this work, we tackle this challenge and propose DepL, a framework attaining dependable learning orchestration. DepL efficiently makes joint, near-optimal decisions concerning (i) which data to use for learning,(ii) the ML models to use – chosen within a set of full-size models and compressed versions thereof – and when to switch from one model to another, and (iii) the clusters of physical nodes to use for the learning. DepL improves over previous works by guaranteeing that the learning quality target (e.g., a minimum loss) is achieved with a target probability, while minimizing the learning (e.g., energy) cost. DepL has provably low polynomial computational complexity and a constant competitive ratio. Further, experimental results using the CIFAR-10 and GTSRB datasets show that it consistently matches the optimum and outperforms state-of-theart approaches (30% faster learning and 40–80% lower cost).  \nIndex Terms—Distributed learning, network support to machine learning, dependable learning, learning guarantees  \nI. INTRODUCTION Two main trends can be observed in the field of machine  \nlearning (ML) models and, especially, deep neural networks (DNNs): on the one hand, their capabilities tend to increase; on the other hand, they require an increasing amount of data and resources for the learning process. To cope with such a shortcoming, two approaches have emerged, to wit, distributed learning and model compression. Distributed learning allows the use of resources and data available at multiple nodes to obtain a faster learning process in a privacy-preserving manner. Model compression, instead, includes a set of related techniques (from model pruning to knowledge distillation) whose high-level purpose is making a simpler model perform like a more complex one, thus transferring the knowledge from the latter to the former.  \nSeveral approaches appeared in the literature have variously combined distributed learning and model compression. Asan example, [1], [2] adapt the resources used for learning.  \nF. Malandrino and C. F. Chiasserini are with CNR-IEIIT and CNIT, Italy.  \nG. Di Giacomo and C. F. Chiasse","cbCaicsYNqQNgBc5","https://ap.wps.com/l/cbCaicsYNqQNgBc5","pdf",2348543,4,1,16,"English","en",105,"# Introduction\n## Distributed learning and model compression\n## Dependability as learning quality guarantees\n# DepL Framework Overview\n## Joint optimization decisions","[{\"question\":\"Why is dependable learning needed for distributed machine learning?\",\"answer\":\"Because many real-world safety- or mission-critical applications require learning quality guarantees, not just good expected loss across executions.\"},{\"question\":\"What decisions does DepL make to achieve dependable learning?\",\"answer\":\"DepL jointly determines which data to use, which ML model to use (among full-size and compressed versions), when to switch models, and which physical node clusters to run learning on.\"},{\"question\":\"How does DepL ensure the learning quality target and control cost?\",\"answer\":\"DepL guarantees that a target learning quality (e.g., minimum loss) is achieved with a specified probability while minimizing the learning cost such as energy.\"}]","Achieving Machine Learning Dependability Through Model Switching and Compression | PDF",1785905068,40,{"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},"achieving-machine-learning-dependability-through-model-switching-and-compression","",{"@graph":37,"@context":86},[38,54,69],{"@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":20},"https://docshare.wps.com/document/achieving-machine-learning-dependability-through-model-switching-and-compression/126438/",{"url":53,"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","2026-08-23","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},"Why is dependable learning needed for distributed machine learning?","Question",{"text":76,"@type":77},"Because many real-world safety- or mission-critical applications require learning quality guarantees, not just good expected loss across executions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What decisions does DepL make to achieve dependable learning?",{"text":81,"@type":77},"DepL jointly determines which data to use, which ML model to use (among full-size and compressed versions), when to switch models, and which physical node clusters to run learning on.",{"name":83,"@type":74,"acceptedAnswer":84},"How does DepL ensure the learning quality target and control cost?",{"text":85,"@type":77},"DepL guarantees that a target learning quality (e.g., minimum loss) is achieved with a specified probability while minimizing the learning cost such as energy.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"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":20,"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":30,"slug":119},7,"Healthcare","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":107,"slug":138},19,"General","general"]