[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126259-en":3,"doc-seo-126259-105":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},126259,2336475104362,"Eden","https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868",8,"Research & Report","Enhancing Knowledge Reusability - A Distributed Multitask Machine Learning Approach","In the Internet of Things era, rapid data growth outpaces current predictive analytics and processing capabilities. Because similar data and analytics tasks can be redundant, patterns from distributed data and models should be extracted so existing schemes can be efficiently reused across distributed computing environments. The core challenge is identifying reusable tasks and tuning models to improve predictive capacity while reusing knowledge. A two-phase Distributed Multi-task Machine Learning framework uses partial learning curves to group similar tasks and then boost candidate reusable models per task group, with analysis and experiments confirming adaptability and reusability in distributed systems.","Long, Q. , Anagnostopoulos, C. and Kolomvatsos, K. (2024) Enhancing knowledge reusability: a distributed multitask machine learning approach. IEEE Transactions on Emerging Topics in Computing,(doi:  10.1109/TETC.2024.3390811)  \nCopyright © 2024 IEEE. Reproduced under a Creative Commons Attribution 4.0  International License.  \nFor the purpose of open access, the author(s) has applied a Creative Commons Attribution license to any Accepted Manuscript version arising.  \n[https://eprints.gla.ac.uk/324545/](https://eprints.gla.ac.uk/324545/)  \nDeposited on: 17 April 2024  \nEnlighten – Research publications by members of the University of Glasgow  \n[https://eprints.gla.ac.uk](https://eprints.gla.ac.uk)  \nEnhancing Knowledge Reusability: A Distributed Multitask Machine Learning Approach  \nQianyu Long, Member, IEEE, Christos Anagnostopoulos, Member, IEEE, Kostas Kolomvatsos  \nAbstract—In the era of the Internet of Things, the unprecedented growth of data surpasses current predictive analytics and processing capabilities. Due to the potential redundancy of similar data and analytics tasks, it is imperative to extract patterns from distributed data and predictive models so that existing schemes can be efficiently reused in distributed computing environments. This is expected to avoid building and maintaining reduplicative predictive models. The fundamental challenge, however, is the detection of reusable tasks and tuning models in order to improve predictive capacity while being reused. We introduce a two-phase Distributed Multi-task Machine Learning (DMtL) framework coping with this challenge. In the first phase, similar tasks are identified and efficiently grouped together according to locally trained models’ performance meta-features, using Partial Learning Curves (PLC). In the subsequent phase, we leverage the PLC-driven DMtL paradigm to boost the performance of candidate reusable models per group of tasks in distributed computing environments. We provide a thorough analysis of our framework along with a comparative assessment against relevant approaches and prior work found in the respective literature. Our experimental results showcase the feasibility of the PLC-driven DMtL method in terms of adaptability and reusability of existing knowledge in distributed computing systems.  \nIndex Terms—Distributed Machine Learning, Knowledge Reuse, Knowledge Management, Multitask Learning.  \nI. INTRODUCTION  \nNowadays, distributed predictive modeling and analytics isan area that attracted significant attention, especially when those analytics are pushed at the edge of the network, a.k.a., Edge Computing paradigm. In parallel, we have witnessed the emergence of distributed learning paradigms, e.g., Federated Learning (FL), and associated challenges including tasks offloading, service migration [16] and distributed data heterogeneity in resource-constrained devices [21] . The scale of computing nodes and the volume of generated data in such environments are increasing explosively. Therefore, (mostly distributed) analytics mechanisms, like predictive and exploratory analysis, should significantly reduce computational and communication resource utilization for training Machine Learning (ML) models by harnessing and re-using, if feasible, existing models and derived knowledge. Motivating examples include predictive analytics in Autonomous Vehicles (AV), where object identification and detection mechanisms are the most critical components to support autonomous driving, e.g., recognizing pedestrians, vehicles, traffic signs, and barriers.  \nQ. Long and C. Anagnostopoulos are with the School of Computing Science, University of Glasgow, UK. K. Kolomvatsos is with the Dept Informatics Telecommunications, University of Thessaly, Greece. This work is partially funded by the EU Horizon 2020 grants TRACE \\#101104278 and SILVANUS \\#101037247 .  \nWhile the number of AVs involved in training object identification models increases, the redundancy of collected d","cbCaifGKK4kaNUTM","https://ap.wps.com/l/cbCaifGKK4kaNUTM","pdf",4183784,7,1,15,"English","en",105,"# Introduction\n## Edge computing and distributed analytics\n## Motivation from redundancy and model reuse\n## Related work and gaps","[{\"question\":\"Why is knowledge reusability important in distributed machine learning?\",\"answer\":\"Because redundancy in data and analytics tasks can waste computation and communication resources, reusing patterns and models helps avoid building and maintaining duplicate predictive models in distributed environments.\"},{\"question\":\"What are the two phases of the proposed Distributed Multi-task Machine Learning framework?\",\"answer\":\"First, similar tasks are identified and grouped using performance meta-features derived from Partial Learning Curves (PLC). Second, the PLC-driven paradigm improves the performance of candidate reusable models for each task group in distributed computing.\"},{\"question\":\"How does the framework help improve predictive capacity while reusing models?\",\"answer\":\"It detects which tasks are reusable and tunes candidate models per group so the reused knowledge generalizes better to the underlying tasks rather than assuming direct plug-and-play reuse.\"}]","Enhancing Knowledge Reusability - A Distributed Multitask Machine Learning Approach | PDF",1785904097,38,{"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},"enhancing-knowledge-reusability-a-distributed-multitask-machine-learning-approach","",{"@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/enhancing-knowledge-reusability-a-distributed-multitask-machine-learning-approach/126259/",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","2026-08-24","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},"Why is knowledge reusability important in distributed machine learning?","Question",{"text":77,"@type":78},"Because redundancy in data and analytics tasks can waste computation and communication resources, reusing patterns and models helps avoid building and maintaining duplicate predictive models in distributed environments.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What are the two phases of the proposed Distributed Multi-task Machine Learning framework?",{"text":82,"@type":78},"First, similar tasks are identified and grouped using performance meta-features derived from Partial Learning Curves (PLC). Second, the PLC-driven paradigm improves the performance of candidate reusable models for each task group in distributed computing.",{"name":84,"@type":75,"acceptedAnswer":85},"How does the framework help improve predictive capacity while reusing models?",{"text":86,"@type":78},"It detects which tasks are reusable and tunes candidate models per group so the reused knowledge generalizes better to the underlying tasks rather than assuming direct plug-and-play reuse.","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},[95,99,103,107,112,117,121,124,129,132,136],{"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":113,"doc_module":4,"doc_module_name":47,"category_name":114,"show_sort_weight":115,"slug":116},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},"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":108,"slug":139},19,"General","general"]