[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119804-en":3,"doc-seo-119804-105":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":20,"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},119804,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Towards explainable automated machine learning","Automated machine learning (AutoML) aims to improve efficiency and accessibility of machine learning methods by automating complex tasks such as model and hyperparameter selection via optimization techniques. Although AutoML systems, especially hyperparameter optimization (HPO), have shown efficiency gains over manual expert-driven workflows, demands for explainability remain largely unmet. This dissertation systematically connects AutoML with Explainable AI and develops methods to enhance explanation quality across model-level, algorithm-mechanism, and AutoML-system-component perspectives.","Towards explainable automated machine learning  \nJulia Moosbauer  \n2023  \nTowards explainable automated machine learning  \nJulia Moosbauer  \nDissertation  \nan der Fakultät für Mathematik, Informatik und Statistik der Ludwig-Maximilians-Universität München  \nvorgelegt von  \nJulia Moosbauer  \naus Bogen  \nMünchen, den 22.02.2023  \nErstgutacher/in: Prof. Dr. Bernd Bischl Zweitgutachter/in: Prof. Dr. Avishek Anand Drittgutachter/in: Prof. Dr. Eyke Hüllermeier Tag der mündlichen Prüfung: 26.05.2023  \nAcknowledgments  \nFirst and foremost, I sincerely thank my supervisor, Prof. Dr. Bernd Bischl, for all his trust, support, and insightful guidance throughout my academic journey so far. I am grateful for the opportunity to delve into a topic that I am passionate about in a supportive and open-minded environment.  \nI would also like to thank Prof. Dr. Avishek Anand and Prof. Dr. Eyke H¨ullermeier for their role as second and third reviewers of this thesis.  \nFurthermore, I want to thank my colleagues for all their support and encouragement, invaluable feedback, and stimulating discussions. Their support and collaboration were especially important during these challenging times of the pandemic. In particular, I would like to express my appreciation to Martin Binder and Julia Herbinger for their exceptional teamwork, and to Janek Thomas and Giuseppe Casalicchio, the Postdocs of the group, for their guidance and valuable advice on various projects.  \nI am also grateful to all my co-authors for their collaborative mindset and fruitful collaborations. My special thanks go to Marius Lindauer, who provided advice and support during our joint research projects.  \nLastly, I would like to thank my family and friends for their unconditional support and encouragement at all times.  \nZusammenfassung  \nAutomatisiertes maschinelles Lernen (AutoML) zielt darauf ab, Effizienz und Zug¨anglichkeit von Methoden des maschinellen Lernens (ML) zu erh¨ohen, indem komplexe Aufgaben wie die Modell-und Hyperparameterauswahl mithilfe von Optimierungsmethoden automatisiert werden. W¨ahrend AutoML-Systeme, insbesondere die Hyperparameter-Optimierung (HPO), im Vergleich zu manuellen, expertengesteuerten Prozessen Effizienzgewinne demonstriert haben, wird die Forderung nach Erkl¨arbarkeit derzeit kaum erf¨ullt.  \nDie Arbeit verbindet die beiden aufstrebenden Bereiche AutoML und Explainable AI auf systematische Weise und tr¨agt mit verschiedenen methodischen Ans¨atzen zu einer verbesserten Erkl¨arbarkeit im Kontext von AutoML bei. Hierbei werden drei Ebenen von Erkl¨arbarkeitsanforderungen unterschieden: Erkl¨arbarkeit des Modells (welches von einem AutoML-System zur¨uckgegeben wird), Erkl¨arbarkeit der induzierenden Mechanismen oder Lernalgorithmen, und Erkl¨arbarkeit der Mechanismen und Komponenten von AutoML-Systemen selbst.  \nDer erste Teil dieser Arbeit befasst sich mit der Anforderung der Erkl¨arbarkeit von Modellen, die von AutoML-Systemen zur¨uckgegeben werden. Der erste Beitrag gibt einen berblick ¨uber die multikriterielle Hyperparameter-Optimierung im Allgemeinen und motiviert Interpretierbarkeit und Modell Sparsity als weitere Ziele von HPO. Im zweiten Beitrag dieser Arbeit wurde eineffizientes multikriterielles HPO-Verfahren entwickelt, das sowohl die pr¨adiktive Performanz als auch die Modell Sparsity als ein Kriterium der Modellerkl¨arbarkeit optimiert.  \nDer zweite Teil der Arbeit befasst sich mit der Erkl¨arbarkeit von Lernalgorithmen oder induzierenden Mechanismen, mit welchen w¨ahrend eines AutoML-Prozesses experimentiert wird. Der dritter Beitrag stellt eine neue Methode vor, die Partial Dependence Plots erweitert, um Effekte von Hyperparametern der Lernalgorithmen auf die pr¨adiktive Performance darzustellen. Die Methode ber¨ucksichtigt post-hoc eine m¨ogliche Stichprobenverzerrung, die typischerweise in den von AutoML-Systemen erzeugten experimentellen Daten vorhanden ist. Im vierten Artikel wird eine Methode vorgestellt, mit der das Problem der Stichprob","cbCaigO93fYX8bRB","https://ap.wps.com/l/cbCaigO93fYX8bRB","pdf",8131657,1,200,"English","en",105,"# Acknowledgments\n# Zusammenfassung\n## AutoML and explainability goals\n## Model explainability in AutoML\n## Explainability of learning algorithms and mechanisms\n## Explainability of AutoML system components","[{\"question\":\"What is the central goal of this dissertation on explainable AutoML?\",\"answer\":\"To systematically combine AutoML and Explainable AI and improve explainability in the AutoML setting across multiple explanation levels.\"},{\"question\":\"Which levels of explainability are distinguished in the work?\",\"answer\":\"Model explainability, explainability of inducing mechanisms or learning algorithms, and explainability of mechanisms and components of AutoML systems themselves.\"},{\"question\":\"How does the dissertation address explainability in hyperparameter optimization?\",\"answer\":\"It proposes multiconstraint/multicriteria HPO approaches and develops methods that target interpretability-related criteria and explanation accuracy under sampling bias.\"}]","Towards explainable automated machine learning | PDF",1785726389,504,{"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},"towards-explainable-automated-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/towards-explainable-automated-machine-learning/119804/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the central goal of this dissertation on explainable AutoML?","Question",{"text":75,"@type":76},"To systematically combine AutoML and Explainable AI and improve explainability in the AutoML setting across multiple explanation levels.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which levels of explainability are distinguished in the work?",{"text":80,"@type":76},"Model explainability, explainability of inducing mechanisms or learning algorithms, and explainability of mechanisms and components of AutoML systems themselves.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the dissertation address explainability in hyperparameter optimization?",{"text":84,"@type":76},"It proposes multiconstraint/multicriteria HPO approaches and develops methods that target interpretability-related criteria and explanation accuracy under sampling bias.","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"]