[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128034-en":3,"doc-seo-128034-105":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},128034,962084931830,"Theodore","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","On Search Space Constraining Methods for Automatic Composition and Optimisation of Machine Learning Pipelines - PhD thesis","Automated machine learning (AutoML) streamlines the steps of collecting, preprocessing, integrating data, composing and optimising ML pipelines, and deploying and maintaining predictive models. ML pipelines combine components for transformation, preprocessing, feature engineering, and prediction tasks. A key AutoML challenge is pipeline composition and optimisation (PCO), which searches within a defined space of components, hyperparameters, and pipeline structures, yet large search spaces make it difficult to locate valid, well-performing pipelines. The dissertation studies strategies to constrain this search space to improve PCO efficiency, proposing AVATAR to filter invalid pipelines via surrogate assessment using a Petri-net on simplified pipelines. It also evaluates noisy opportunistic meta-knowledge from past PCO runs and explores search-space reduction strategies, showing that non-extreme reduction and problem-informed knowledge improve results and can support dynamic future control.","UNIVERSITY OF TECHNOLOGY SYDNEY Faculty of Engineering and Information Technology  \nOn Search Space Constraining Methods for Automatic Composition and Optimisation of Machine Learning  \nPipelines  \nA thesis submitted in ful􀀌llment of the requirements for the degree of  \nDoctor of Philosophy  \nby  \nTien Dung NGUYEN  \nMarch 2023  \nCerti􀀌cate of Original Authorship  \nI, Tien Dung NGUYEN, declare that this thesis, is submitted in ful􀀌lment of the requirements for the award of the [Ph.D. degree](Ph.D. degree), in the Faculty of Engineering and Information Technology at the University of Technology Sydney.  \nThis thesis is wholly my own work unless otherwise reference or acknowledged. In addition, I certify that all information sources and literature used are indicated in the thesis.  \nThis document has not been submitted for quali􀀌cations at any other academic institution.  \nThis research is supported by the Australian Government Research Training Program.  \nProduction Note:  \nSignature: Signature removed prior to publication.  \nDate: 09/03/2023  \nAbstract  \nAutomated machine learning (AutoML) has been developed and studied to automate the process of collecting, preprocessing and integrating data, composing and optimising ML pipelines, and deploying and maintaining predictive models. A machine learning (ML) pipeline is a work o w consisting of many components to perform data transformation, data preprocessing, feature engineering and classi􀀌cation/regression tasks. ML pipelines have been used to build predictive models for a variety of ML problems. One of the most important research topics of AutoML is ML pipeline composition and optimisation (PCO) . PCO processes search for valid and well-performing ML pipelines in a given search space. A search space consists of ML components, i.e. preprocessing and predictor/meta-predictor components, components' hyperparameters and pipeline structures that link ML components. Due to the large size of search spaces, it is challenging for PCO processes to 􀀌nd valid and well-performing pipelines. The aim of the dissertation is to study methods/strategies to constrain a search space to enable PCO processes to more easily and e􀀎ciently 􀀌nd valid and well-performing pipelines. This dissertation has three main contributions. The 􀀌rst contribution is a novel method, AVATAR, to constrain search space to consider only valid ML pipelines. The AVATAR eliminates invalid pipelines by assessing ML pipeline validity using a surrogate model, a Petri-net approach based on consideration of simpli􀀌ed pipelines not requiring the use of training data or its processing. The second contribution is a critical evaluation of the so called \"opportunistic\" meta-knowledge based on previous experience in the form of PCO runs and predictor evaluations with default hyperparameters. Although such meta-knowledge is inherently noisy and with high statistical variability, we found that it is still very useful for constraining search spaces with promising, well-performing ML components. The third contribution is an exploration of di􀀋erent search space reduction strategies employing that meta-knowledge.  \nThe results show that the reduction of search space should not be extreme. In addition, reducing the search space based on the knowledge of the problem itself enables PCO processes to deliver the best-performing ML pipelines, followed by the knowledge of strong general performers. Finally, the results obtained in this study can form the basis of and be extended in the future to dynamically control search spaces to 􀀌nd better ML pipelines by combining the knowledge of the ML problems solved in the past and the knowledge of the problem itself acquired from the run of the PCO processes.  \nContents  \nCerti􀀌cate i  \nAbstract ii  \nDedication viii  \nAcknowledgments ix  \nList of Publications x  \nList of Figures xii  \nList of Tables xxxi  \nList of Abbreviations xxxvi  \nList of Notations xxxix  \nChapter 1 Introduction .......................","cbCaietSa5liwhXV","https://ap.wps.com/l/cbCaietSa5liwhXV","pdf",10547826,2,1,326,"English","en",105,"# Chapter 1 Introduction\n## Background\n## Motivation\n## The Problem of ML Pipeline Composition and Optimisation with Constrained Configuration Spaces\n## Research Question and Objectives\n## Original Contributions\n## Thesis Organisation\n# Chapter 2 Literature Review\n## Introduction\n## The Fundamentals of ML Pipeline Composition and Optimisation\n## Formal Representation of Pipeline\n## ML Pipeline Composition & Optimisation\n## Configuration Space Reduction","[{\"question\":\"What problem does the dissertation address in AutoML pipeline composition and optimisation (PCO)?\",\"answer\":\"It addresses the difficulty of finding valid and well-performing ML pipelines when the search space is large, making PCO computationally challenging.\"},{\"question\":\"What is AVATAR and how does it constrain the search space?\",\"answer\":\"AVATAR constrains the search space by considering only valid ML pipelines, eliminating invalid ones through surrogate-model assessment based on a Petri-net approach using simplified pipelines.\"},{\"question\":\"What do the results indicate about search space reduction strategy?\",\"answer\":\"The results show reduction should not be extreme, and that using knowledge of the problem itself (and then strong general performers) helps PCO deliver better ML pipelines.\"}]","On Search Space Constraining Methods for Automatic Composition and Optimisation of Machine Learning Pipelines - PhD thesis | PDF",1785944220,822,{"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},"on-search-space-constraining-methods-for-automatic-composition-and-optimisation-of-machine-learning-pipelines-phd-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/on-search-space-constraining-methods-for-automatic-composition-and-optimisation-of-machine-learning-pipelines-phd-thesis/128034/",4,{"url":52,"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","2026-08-29","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},"What problem does the dissertation address in AutoML pipeline composition and optimisation (PCO)?","Question",{"text":76,"@type":77},"It addresses the difficulty of finding valid and well-performing ML pipelines when the search space is large, making PCO computationally challenging.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What is AVATAR and how does it constrain the search space?",{"text":81,"@type":77},"AVATAR constrains the search space by considering only valid ML pipelines, eliminating invalid ones through surrogate-model assessment based on a Petri-net approach using simplified pipelines.",{"name":83,"@type":74,"acceptedAnswer":84},"What do the results indicate about search space reduction strategy?",{"text":85,"@type":77},"The results show reduction should not be extreme, and that using knowledge of the problem itself (and then strong general performers) helps PCO deliver better ML pipelines.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"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":119,"slug":120},7,"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":107,"slug":139},19,"General","general"]