[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120163-en":3,"doc-seo-120163-105":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},120163,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","FEDERATED MACHINE LEARNING - Privacy, Explainability, and Performance - Master Thesis","Federated Machine Learning - Privacy, Explainability, and Performance examines trade-offs between privacy and model behavior for inherently explainable machine learning and deep learning. It studies whether federated learning affects performance and explainability of Takagi-Sugeno-Kang fuzzy rule-based systems and deep models. Central and federated variants are trained on ten datasets using i.i.d data with five collaborators. Experiments indicate federated learning does not significantly degrade results and preserves rule-based transparency.","FEDERATED MACHINE LEARNING: PRIVACY, EXPLAINABILITY, AND PERFORMANCE  \nHALVOR SKRIBELAND  \nSUPERVISOR  \nChristian Walter Peter Omlin  \nUniversity of Agder, 2024  \nFaculty of Engineering and Science  \nDepartment of Information and Communication Technology  \nObligatorisk gruppeerklæring  \nDen enkelte student er selv ansvarlig for å sette seg inn i hva som er lovlige hjelpemidler, retningslinjer for bruk av disse og regler om kildebruk. Erklæringen skal bevisstgjøre studentene på deres ansvar og hvilke konsekvenserfusk kan medføre. Manglende erklæring fritar ikke studentene fra sitt ansvar.  \n\n| 1. | Vi erklærer herved at vår besvarelse er vårt eget arbeid, og at vi ikke har brukt andre kilder eller har mottatt annen hjelp enn det som er nevnt i besvarelsen. | Ja |\n| --- | --- | --- |\n| 2. | Vi erklærer videre at denne besvarelsen:\u003Cbr>• Ikke har vært brukt til annen eksamen ved annenavdeling/universitet/høgskole innenlands eller utenlands.\u003Cbr>• Ikke refererer til andres arbeid uten at det er oppgitt.\u003Cbr>• Ikke refererer til eget tidligere arbeid uten at det er oppgitt.\u003Cbr>• Har alle referansene oppgitt i litteraturlisten.\u003Cbr>• Ikke er en kopi, duplikat eller avskrift av andres arbeid eller besvarelse. | Ja |\n| 3. | Vi er kjent med at brudd på ovennevnte er å betrakte som fusk og kan medføre annullering av eksamen og utestengelse fra universiteter og høgskoler i Norge, jf. Universitets-og høgskoleloven §§4-7 og 4-8 og Forskrift om eksamen §§ 31 . | Ja |\n| 4. | Vi er kjent med at alle innleverte oppgaver kan bli plagiatkontrollert. | Ja |\n| 5. | Vi er kjent med at Universitetet i Agder vil behandle alle saker hvor det forliggermistanke om fusk etter høgskolens retningslinjer for behandling av saker omfusk. | Ja |\n| 6. | Vi har satt oss inn i regler og retningslinjer i bruk av kilder og referanser på biblioteket sine nettsider. | Ja |\n| 7. | Vihar i flertall blitt enige om at innsatsen innad i gruppen er merkbart forskjellig og ønsker dermed å vurderes individuelt. Ordinært vurderes alle deltakere iprosjektet samlet. | Ja |\n\nPubliseringsavtale  \nFullmakt til elektronisk publisering av oppgaven Forfatter(ne) har opphavsrett til oppgaven. Det betyr blant annetenerett til å gjøre verket tilgjengelig for allmennheten (Åndsverkloven. §2) .  \nOppgaver som er unntatt offentlighet eller taushetsbelagt/konfidensiell vil ikke bli publisert.  \n\n| Vi gir herved Universitetet i Agder en vederlagsfri rett til å gjøre oppgaven tilgjengelig forelektronisk publisering: | Ja |\n| --- | --- |\n| Er oppgaven båndlagt (konfidensiell)? | Nei |\n| Er oppgaven unntatt offentlighet? | Nei |\n\nAcknowledgements  \nI would like to express my deepest gratitude to my supervisor, Professor Christian Walter Peter Omlin for their guidance and deep insights throughout this thesis.  \nAbstract  \nThere is an increasing need for explainable and private machine learning. The European Union’s AI Act is a recent legislation aimed at regulating the development and use of artificial intelligence in the European Union. Trustworthy AI is an important part of this, and some of the key requirements for trustworthy AI are data privacy and model transparency. Takagi-Sugeno-Kang fuzzy rule-based systems (TSK-FRBS) are inherently explainable, and federated learning (FL) is a way to train machine learning (ML) models while ensuring data privacy. Training an inherently explainable ML model using FL has the potential to ensure data privacy while training a transparent model.  \nThis thesis empirically investigates the possible trade-offs between privacy and the performance of inherently explainable ML models and deep learning (DL) models. Does federated learning reduce the performance of either TSK-FRBS or deep learning models? To answer this question, a central TSK-FRBS, a federated TSK-FRBS, a central DL, and a federated DL model have been implemented on ten different datasets from different application areas.  \nThe federated models have been trained using i.i.d data and five collaborators","cbCaisTN1gK5IbTi","https://ap.wps.com/l/cbCaisTN1gK5IbTi","pdf",786407,1,67,"English","en",105,"# Introduction\n## Research Question\n## Contribution\n## Structure\n# Background / Literature Review\n## AI Act\n## Explainable AI (XAI)\n### Achieve explainability\n### Fuzzy Rule-Based Systems\n### Takagi-Sugeno-Kang FRBS\n## Privacy Preserving Machine Learning\n### Federated Learning (FL)\n## Deep Learning\n# State of the art\n## XAI and FL\n# Methodology\n## Research design\n## Implementation\n### Central and federated TSK-FRBS\n### Central and federated deep learning","[{\"question\":\"What is the main research question of the thesis?\",\"answer\":\"The thesis investigates whether federated learning reduces the performance and/or explainability of inherently explainable TSK-FRBS models or deep learning models.\"},{\"question\":\"How were the federated and central models trained and evaluated?\",\"answer\":\"The work implements central and federated versions of TSK-FRBS and deep learning, training them on ten datasets using i.i.d data with five collaborators, then comparing performance and explainability.\"},{\"question\":\"What do the experiments show about the impact of federated learning?\",\"answer\":\"Federated learning does not significantly affect performance or explainability compared with central training on the same datasets, and deep learning performs slightly better overall with some exceptions.\"}]","FEDERATED MACHINE LEARNING - Privacy, Explainability, and Performance - Master Thesis | PDF",1785728506,169,{"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},"federated-machine-learning-privacy-explainability-and-performance-master-thesis","",{"@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/federated-machine-learning-privacy-explainability-and-performance-master-thesis/120163/",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","2026-08-03",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},"What is the main research question of the thesis?","Question",{"text":75,"@type":76},"The thesis investigates whether federated learning reduces the performance and/or explainability of inherently explainable TSK-FRBS models or deep learning models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the federated and central models trained and evaluated?",{"text":80,"@type":76},"The work implements central and federated versions of TSK-FRBS and deep learning, training them on ten datasets using i.i.d data with five collaborators, then comparing performance and explainability.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the experiments show about the impact of federated learning?",{"text":84,"@type":76},"Federated learning does not significantly affect performance or explainability compared with central training on the same datasets, and deep learning performs slightly better overall with some exceptions.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]