[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119212-en":3,"doc-seo-119212-105":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},119212,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","THE IMPACT OF GRAPH EMBEDDINGS ON ENHANCING MACHINE LEARNING MODELS - Master’s Thesis","This thesis investigates enhancing poor-quality datasets—limited in features or with weak feature relevance—by integrating knowledge graph embeddings to improve machine learning performance on classification and regression tasks. The work extends OWL2Vec* and evaluates TransE and extended OWL2Vec* embeddings, showing effectiveness depends on the presence and representation of correlated features in the knowledge graph. Results indicate OWL2Vec* is more versatile for interpreting entities as classes or attributes, while TransE captures relationships between entities more clearly, emphasizing carefully designed knowledge graphs.","THE IMPACT OF GRAPH EMBEDDINGS ON ENHANCING MACHINE LEARNING MODELS  \nLIAM JAMES GLENNIE ENGLAND  \nThesis supervisor  \nANNA QUERALT CALAFAT (Department of Service and Information System Engineering)  \nDegree  \nMaster's Degree in Data Science  \nMaster's thesis  \nFacultat d'Informàtica de Barcelona (FIB) Universitat Politècnica de Catalunya (UPC) -BarcelonaTech  \n26/06/2024  \nAcknowledgements  \nI would like to express my deepest gratitude to my supervisor, Anna Queralt Calafat, for her constant support and invaluable feedback throughout this thesis. Her guidance was essential to the success of this work.  \nI am also thankful to my friends and family for their unwavering support and for providing muchneeded distractions when necessary. Their encouragement and patience were vital in helping me complete this thesis.  \nAbstract  \nThis thesis investigates the enhancement of poor-quality datasets, characterised by a limited number of features or features poorly related to a machine learning problem, by integrating knowledge graph embeddings to boost the performance of machine learning models in classification and regression tasks. The study introduces an extension of OWL2Vec* and assesses the effectiveness of the TransE and extended OWL2Vec* embeddings, revealing that their usefulness for regression and classifications tasks is highly dependent on the presence and representation of correlated features within the knowledge graph. Findings indicate that OWL2Vec* is more versatile when interpreting information in different forms, being most effective in handling relevant features as classes or attributes. On the other hand, results show that TransE understands relationships between entities better than OWL2Vec* . The research underscores the significance of meticulously designed knowledge graphs and proposes future work to achieve potentially superior embeddings.  \n1 Table of Contents  \nContents  \n1 Table of Contents 4  \n2 Introduction 7  \n3 Motivation 9  \n4 Related Work 11  \n4.1 Translation Method Algorithms ............................ 11  \n4.2 Matrix Factorisation Algorithms ........................... 11  \n4.3 Deep Learning Algorithms ............................... 11  \n4.4 Experimental Evaluations of KG Embeddings .................... 11  \n4.5 Dataset Enrichment with KGs ............................. 12  \n5 Background 13  \n5.1 Knowledge Graph .................................... 13  \n5.1.1 RDF ....................................... 14  \n5.1.2 RDF-S ...................................... 15  \n5.1.3 OWL ...................................... 15  \n5.2 Embeddings ....................................... 17  \n5.3 Knowledge Graph Embeddings ............................ 18  \n5.3.1 TransE ..................................... 18  \n5.3.2 RDF2Vec .................................... 19  \n5.3.3 OWL2Vec* ................................... 20  \n6 Methodology 23  \n6.1 Process ......................................... 23  \n6.2 Datasets ......................................... 23  \n6.3 OWL Graphs ...................................... 25  \n6.4 Embedding Algorithms and Modifications ...................... 29  \n6.4.1 OWL2Vec* Original Implementation ..................... 30  \n6.4.2 OWL2Vec* Extended Implementation .................... 30  \n6.4.3 TransE ..................................... 30  \n6.5 Machine Learning Models ............................... 31  \n6.5.1 Classification Models .............................. 32  \n6.5.2 Regression Models ............................... 33  \n6.6 Clustering ........................................ 33  \n6.7 Ethical Implications .................................. 33  \n7 Results 34  \n7.1 OWL2Vec* Implementation Comparison ....................... 34  \n7.2 Classification Models .................................. 34  \n7.3 Regression Models ................................... 37  \n7.4 Clustering ........................................ 38  \n8 Conclusion 40  \n8.1 Personal Reflection ..................................","cbCaifaeIAyl5OBl","https://ap.wps.com/l/cbCaifaeIAyl5OBl","pdf",2644455,1,53,"English","en",105,"# Table of Contents\n## Introduction\n## Motivation\n## Related Work\n## Background\n## Methodology\n## Results\n## Conclusion\n## Annex","[{\"question\":\"How does the thesis use knowledge graph embeddings to improve machine learning models?\",\"answer\":\"It integrates knowledge graph embeddings to enrich poor-quality datasets, improving model performance in classification and regression by leveraging structured information from the knowledge graph.\"},{\"question\":\"What is the role of the OWL2Vec* extension and how is it evaluated?\",\"answer\":\"The study introduces an extension of OWL2Vec* and compares its effectiveness against TransE and the extended OWL2Vec* embeddings through experiments on classification, regression, and clustering.\"},{\"question\":\"Why does the usefulness of embeddings depend on the dataset features?\",\"answer\":\"Findings show performance is highly dependent on whether the knowledge graph contains and represents correlated features relevant to the target tasks.\"}]","THE IMPACT OF GRAPH EMBEDDINGS ON ENHANCING MACHINE LEARNING MODELS - Master’s Thesis | PDF",1785723128,134,{"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},"the-impact-of-graph-embeddings-on-enhancing-machine-learning-models-masters-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/the-impact-of-graph-embeddings-on-enhancing-machine-learning-models-masters-thesis/119212/",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},"How does the thesis use knowledge graph embeddings to improve machine learning models?","Question",{"text":75,"@type":76},"It integrates knowledge graph embeddings to enrich poor-quality datasets, improving model performance in classification and regression by leveraging structured information from the knowledge graph.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the role of the OWL2Vec* extension and how is it evaluated?",{"text":80,"@type":76},"The study introduces an extension of OWL2Vec* and compares its effectiveness against TransE and the extended OWL2Vec* embeddings through experiments on classification, regression, and clustering.",{"name":82,"@type":73,"acceptedAnswer":83},"Why does the usefulness of embeddings depend on the dataset features?",{"text":84,"@type":76},"Findings show performance is highly dependent on whether the knowledge graph contains and represents correlated features relevant to the target tasks.","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"]