[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117413-en":3,"doc-seo-117413-105":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},117413,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learning","Hybrid intelligence enhances decision-making and problem-solving by combining human cognitive strengths with artificial intelligence. With Large Language Models increasingly acting as smart agents, hybrid intelligence becomes central to accelerating machine learning while maintaining effective human-machine interaction. The paper targets sustainability and energy-aware development by addressing a common gap: optimizing final model quality while neglecting the energy cost of the optimization process. It proposes interactive inclusion of secondary knowledge via human-in-the-loop and LLM agents to diagnose and resolve inefficiencies across development.","Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learning  \nDaniel Geißler  \n[daniel.geissler@dfki.de](daniel.geissler@dfki.de)[ ](daniel.geissler@dfki.de)DFKI  \nKaiserslautern, Germany  \nPaul Lukowicz  \n[paul.lukowicz@dfki.de](paul.lukowicz@dfki.de)[ ](paul.lukowicz@dfki.de)DFKI  \nUniversity of Kaiserslautern-Landau Kaiserslautern, Germany  \narXiv :2407 . 10580v 1 [ cs .AI] 15 Jul 2024  \nABSTRACT  \nHybrid intelligence aims to enhance decision-making, problemsolving, and overall system performance by combining the strengths of both, human cognitive abilities and artificial intelligence. With the rise of Large Language Models (LLM), progressively participating as smart agents to accelerate machine learning development, Hybrid Intelligence is becoming an increasingly important topic for effective interaction between humans and machines. This paper presents an approach to leverage Hybrid Intelligence towards sustainable and energy-aware machine learning. When developing machine learning models, final model performance commonly rules the optimization process while the efficiency of the process itself is often neglected. Moreover, in recent times, energy efficiency has become equally crucial due to the significant environmental impact of complex and large-scale computational processes. The contribution of this work covers the interactive inclusion of secondary knowledge sources through Human-in-the-loop (HITL) and LLM agents to stress out and further resolve inefficiencies in the machine learning development process.  \nCCS CONCEPTS  \n• Human-centered computing → Visualization systems and tools; Interactive systems and tools; Systems and tools for interaction design.  \nKEYWORDS  \nHybrid Intelligence, Interactivity, Sustainability, Energy Awareness  \nACM Reference Format:  \nDaniel Geißler and Paul Lukowicz. 2024. Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learning. In Companion of the 2024 ACM International Joint Conference on Pervasive and Ubiquitous Computing Pervasive and Ubiquitous Computing (UbiComp Companion ’24), October 5–9, 2024, Melbourne, VIC, Australia. ACM, New York, NY, USA, 5 pages. [https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \n1 PROBLEM STATEMENT  \nThe field of sustainable machine learning has witnessed increasing relevance in recent years, driven by the fast-paced expansion of machine learning applications in pervasive systems [28] . Even though  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s) .  \nUbiComp Companion ’24, October 5–9, 2024, Melbourne, VIC, Australia © 2024 Copyright held by the owner/author(s) .  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nthe efficiency, considering hardware from low-power embedded devices to high-performance clusters, has improved over time, it cannot keep up with the rapidly increasing amount of devices that are utilized in our daily lives [9]. When it comes to energy-efficient optimization, research commonly focuses on optimizing for time reduction instead of energy [19]. However, shrinking time commonly requires even more computational resources to counteract.  \nFrom the data-level perspective, the quality of training data significantly impacts the final performance of machine learning models [25] . Small nuances in data quality, such as issues arising from sensor quality, placement, and annotation, can drastically affect the overall model performance, especially in the fields of Human Activity Recognition HAR [29] . These imperfections lead to inefficient utilization of resources, as weak data quality necessitates additio","cbCaicHSwERT3xJi","https://ap.wps.com/l/cbCaicHSwERT3xJi","pdf",1651740,1,5,"English","en",105,"# Problem Statement\n## Energy tracking and awareness gap\n## Data quality and resource inefficiency\n## Measuring energy consumption for training\n## Why inefficiencies occur and how hybrid intelligence helps\n# Related Work\n## Energy Tracking","[{\"question\":\"Why does the paper focus on energy-aware machine learning development?\",\"answer\":\"Model training often prioritizes final performance while overlooking the energy cost of optimization. The growing environmental impact of large-scale computation makes energy awareness equally crucial.\"},{\"question\":\"What role does hybrid intelligence play in addressing ML inefficiencies?\",\"answer\":\"Hybrid intelligence integrates additional knowledge through visual and numeric analysis, enabling computational resource savings during model optimization and helping explain why inefficiencies happen.\"},{\"question\":\"How does the proposed approach include secondary knowledge during development?\",\"answer\":\"The work covers interactive inclusion of secondary knowledge sources using Human-in-the-loop (HITL) and LLM agents to identify and resolve inefficiencies in the machine learning development process.\"}]","Leveraging Hybrid Intelligence Towards Sustainable and Energy-Efficient Machine Learning | PDF",1785675739,13,{"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},"leveraging-hybrid-intelligence-towards-sustainable-and-energy-efficient-machine-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/leveraging-hybrid-intelligence-towards-sustainable-and-energy-efficient-machine-learning/117413/",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},"Why does the paper focus on energy-aware machine learning development?","Question",{"text":75,"@type":76},"Model training often prioritizes final performance while overlooking the energy cost of optimization. The growing environmental impact of large-scale computation makes energy awareness equally crucial.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What role does hybrid intelligence play in addressing ML inefficiencies?",{"text":80,"@type":76},"Hybrid intelligence integrates additional knowledge through visual and numeric analysis, enabling computational resource savings during model optimization and helping explain why inefficiencies happen.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed approach include secondary knowledge during development?",{"text":84,"@type":76},"The work covers interactive inclusion of secondary knowledge sources using Human-in-the-loop (HITL) and LLM agents to identify and resolve inefficiencies in the machine learning development process.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":21,"slug":137},19,"General","general"]