[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117570-en":3,"doc-seo-117570-105":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},117570,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","AutoRDF2GML - Facilitating RDF Integration in Graph Machine Learning","AutoRDF2GML is a framework that converts RDF data into graph machine learning-ready representations by generating both content-based features from RDF datatype properties and topology-based features from RDF object properties. Automated feature extraction enables users with limited RDF and SPARQL expertise to produce datasets for link prediction, node classification, and graph classification. The work also introduces four new benchmark datasets built from large RDF knowledge graphs, supporting evaluation of GNN and related approaches and bridging the gap between graph machine learning and the semantic web.","arXiv :2407 . 18735v 1 [ cs .LG] 26 Jul 2024  \nAutoRDF2GML: Facilitating RDF Integration in Graph Machine Learning  \nMichael F¨arber 1, David Lamprecht2, and Yuni Susanti3  \n1 ScaDS.AI & TU Dresden, Dresden, Germany  \nmichael .faerber@tu-dresden .de  \n2 metaphacts GmbH, Walldorf, Germany  \n[dl@metaphacts.com](dl@metaphacts.com)  \n3 Fujitsu Ltd. , Japan  \n[yuni.susanti@fujitsu.com](yuni.susanti@fujitsu.com)  \nAbstract. In this paper, we introduce AutoRDF2GML, a framework designed to convert RDF data into data representations tailored for graph machine learning tasks. AutoRDF2GML enables, for the first time, the creation of both content-based features—i.e., features based on RDF datatype properties—and topology-based features—i.e., features based on RDF object properties. Characterized by automated feature extraction, AutoRDF2GML makes it possible even for users less familiar with RDF and SPARQL to generate data representations ready for graph machine learning tasks, such as link prediction, node classification, and graph classification. Furthermore, we present four new benchmark datasets for graph machine learning, created from large RDF knowledge graphs using our framework. These datasets serve as valuable resources for evaluating graph machine learning approaches, such as graph neural networks. Overall, our framework effectively bridges the gap between the Graph Machine Learning and Semantic Web communities, paving the way for RDF-based machine learning applications.  \nCode & Framework: [https://github.com/davidlamprecht/AutoRDF2GML/](https://github.com/davidlamprecht/AutoRDF2GML/)  \nMIT License  \nGML Dataset LP WC: [https://doi.org/10.5281/zenodo.10299366](https://doi.org/10.5281/zenodo.10299366)  \nCC BY-SA 4.0 License  \nGML Dataset SOA-SW: [https://doi.org/10.5281/zenodo.10299429](https://doi.org/10.5281/zenodo.10299429)  \nCreative Commons Zero (CC0)  \nGML Dataset AIFB: [https://doi.org/10.5281/zenodo.10989595](https://doi.org/10.5281/zenodo.10989595)  \nCC BY 4.0 License  \nGML Dataset LinkedMDB: [https://doi.org/10.5281/zenodo.10989683](https://doi.org/10.5281/zenodo.10989683)  \nCC BY 4.0 License  \n1 Introduction  \nKnowledge representation based on RDF is designed to be interpretable by both humans and machines. Integrating RDF with graph machine learning, such as in Graph Neural Network (GNN) approaches, however, presents significant challenges, as RDF differs remarkably from the data representations used in machine learning. The primary challenge lies in modeling entity relationships and  \n2 M. F¨arber et al.  \nattributes as feature vectors, diverging from RDF with its explicit knowledge representation. Additionally, the inherent heterogeneity (variety of entity and relation types) and sparsity of RDF data (few relations per entity) potentially affect the consistency and robustness of the learning process [50,51] .  \nExisting frameworks for preparing RDF data for graph machine learning (GML) tasks typically lack the capability to transform RDF data into a propositionalized format, such as a feature matrix format. Instead, they convert RDF data into a standard feature matrix without considering the graph structure [3] . Thus, they currently ignore both the different entity types and the object properties of RDF instances, which are crucial parts of RDF data.  \nFurthermore, current benchmarks in graph machine learning, such as those provided by PyTorch Geometric, differ in the provisioning of node features, i.e. , the modeling of nodes. Typically, we can categorize the available node features for datasets for graph machine learning into the following types: (1) contentbased natural language descriptions (NLD),(2) other content-based literals (e.g. , numeric, categorical, or boolean values), and (3) topology-based features that encapsulate the graph structure [16,36,25] . While existing benchmarks cover both homogeneous and heterogeneous graphs, they focus on different aspects. For homogeneous graphs, they typically prioriti","cbCairhyDjOW5rD2","https://ap.wps.com/l/cbCairhyDjOW5rD2","pdf",595423,1,19,"English","en",105,"# Introduction\n## RDF and Graph Machine Learning Challenges\n## Existing GML Frameworks and Benchmarks\n## AutoRDF2GML Framework and Contributions","[{\"question\":\"What does AutoRDF2GML convert RDF data into for graph machine learning tasks?\",\"answer\":\"It converts RDF data into graph machine learning-ready heterogeneous graph datasets with numeric node features represented as feature matrices.\"},{\"question\":\"How does AutoRDF2GML generate node features?\",\"answer\":\"It creates content-based features from RDF datatype properties and topology-based features from RDF object properties, using automated feature extraction.\"},{\"question\":\"What additional resources does the paper provide beyond the framework itself?\",\"answer\":\"It presents four new benchmark datasets derived from large RDF knowledge graphs to evaluate graph machine learning approaches such as graph neural networks.\"}]","AutoRDF2GML - Facilitating RDF Integration in Graph Machine Learning | PDF",1785677046,48,{"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},"autordf2gml-facilitating-rdf-integration-in-graph-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/autordf2gml-facilitating-rdf-integration-in-graph-machine-learning/117570/",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},"What does AutoRDF2GML convert RDF data into for graph machine learning tasks?","Question",{"text":75,"@type":76},"It converts RDF data into graph machine learning-ready heterogeneous graph datasets with numeric node features represented as feature matrices.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does AutoRDF2GML generate node features?",{"text":80,"@type":76},"It creates content-based features from RDF datatype properties and topology-based features from RDF object properties, using automated feature extraction.",{"name":82,"@type":73,"acceptedAnswer":83},"What additional resources does the paper provide beyond the framework itself?",{"text":84,"@type":76},"It presents four new benchmark datasets derived from large RDF knowledge graphs to evaluate graph machine learning approaches such as graph neural networks.","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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]