{"id":"https://openalex.org/W3211044875","doi":"https://doi.org/10.1145/3459637.3481999","title":"DistRDF2ML - Scalable Distributed In-Memory Machine Learning Pipelines for RDF Knowledge Graphs","display_name":"DistRDF2ML - Scalable Distributed In-Memory Machine Learning Pipelines for RDF Knowledge Graphs","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3211044875","doi":"https://doi.org/10.1145/3459637.3481999","mag":"3211044875"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3481999","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3481999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/7665860","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090201900","display_name":"Carsten Felix Draschner","orcid":"https://orcid.org/0000-0002-1006-146X"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carsten Felix Draschner","raw_affiliation_strings":["University of Bonn, Bonn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030333280","display_name":"Claus Stadler","orcid":"https://orcid.org/0000-0001-9948-6458"},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claus Stadler","raw_affiliation_strings":["University of Leipzig, Leipzig, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leipzig, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023256605","display_name":"Farshad Bakhshandegan Moghaddam","orcid":null},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Farshad Bakhshandegan Moghaddam","raw_affiliation_strings":["University of Bonn, Bonn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bonn, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067133778","display_name":"Jens Lehmann","orcid":"https://orcid.org/0000-0001-9108-4278"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Lehmann","raw_affiliation_strings":["University of Bonn & Fraunhofer IAIS, Bonn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bonn & Fraunhofer IAIS, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034642813","display_name":"Hajira Jabeen","orcid":"https://orcid.org/0000-0003-1476-2121"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hajira Jabeen","raw_affiliation_strings":["University of Cologne, Cologne, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cologne, Cologne, Germany","institution_ids":["https://openalex.org/I180923762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1195,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82740507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4465","last_page":"4474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8434875011444092},{"id":"https://openalex.org/keywords/rdf","display_name":"RDF","score":0.5987927317619324},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5777084827423096},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49272945523262024},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.4817500114440918},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.46077603101730347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43241751194000244},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4108280837535858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37585166096687317},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3488212525844574},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.3233978748321533},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27070796489715576},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.266296923160553},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1357426643371582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8434875011444092},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.5987927317619324},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5777084827423096},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49272945523262024},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4817500114440918},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.46077603101730347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43241751194000244},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4108280837535858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37585166096687317},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3488212525844574},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.3233978748321533},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27070796489715576},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.266296923160553},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1357426643371582}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3459637.3481999","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3481999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:7665860","is_oa":true,"landing_page_url":"https://zenodo.org/record/7665860","pdf_url":"https://zenodo.org/record/7665860","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"pmh:oai:fraunhofer.de:N-644503","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-644503.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IAIS","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/413333","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/413333","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:7665860","is_oa":true,"landing_page_url":"https://zenodo.org/record/7665860","pdf_url":"https://zenodo.org/record/7665860","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8503435168","display_name":null,"funder_award_id":"872592","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320328368","display_name":"South African National Space Agency","ror":"https://ror.org/02epph894"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3211044875.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W23685451","https://openalex.org/W2022166150","https://openalex.org/W2080133951","https://openalex.org/W2087159174","https://openalex.org/W2100417396","https://openalex.org/W2127795553","https://openalex.org/W2523679382","https://openalex.org/W2797862701","https://openalex.org/W2984509121","https://openalex.org/W2997591727","https://openalex.org/W3215356745"],"related_works":["https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2799508461","https://openalex.org/W2776293731","https://openalex.org/W2610919777","https://openalex.org/W2965230088","https://openalex.org/W1534806717","https://openalex.org/W4293389049","https://openalex.org/W4243630814"],"abstract_inverted_index":{"This":[0,24],"paper":[1],"presents":[2],"DistRDF2ML,":[3],"the":[4,46,79,81,84,98,112,116,134,165,185],"generic,":[5],"scalable,":[6],"and":[7,57,83,107,122,141,156,175,180],"distributed":[8,172],"framework":[9,25,126,163],"for":[10,16,70],"creating":[11,71],"in-memory":[12],"data":[13,33,62,176],"preprocessing":[14],"pipelines":[15,190],"Spark-based":[17],"machine":[18,72,108,117],"learning":[19,73,109,118],"on":[20],"RDF":[21,32],"knowledge":[22,50,100,169],"graphs.":[23,51],"introduces":[26],"software":[27,55],"modules":[28,42,76],"that":[29,65,92],"transform":[30],"large-scale":[31],"into":[34,133],"ML-ready":[35],"fixed-length":[36],"numeric":[37],"feature":[38],"vectors.":[39],"The":[40,75,102,124,162],"developed":[41],"are":[43,86],"optimized":[44],"to":[45,96],"multi-modal":[47],"nature":[48],"of":[49,105,114,127,168,183,187,195],"DistRDF2ML":[52,128,146],"provides":[53],"aligned":[54],"design":[56,150],"usage":[58],"principles":[59],"as":[60,88],"common":[61],"science":[63],"stacks":[64],"offer":[66],"an":[67],"easy-to-use":[68],"package":[69],"pipelines.":[74],"used":[77,95],"in":[78,139],"pipeline,":[80],"hyper-parameters":[82],"results":[85,110],"exported":[87],"a":[89,192],"semantic":[90,103],"structure":[91],"can":[93],"be":[94],"enrich":[97],"original":[99],"graph.":[101],"representation":[104],"metadata":[106],"offers":[111,181],"advantage":[113],"increasing":[115],"pipelines'":[119],"reusability,":[120],"explainability,":[121],"reproducibility.":[123],"entire":[125],"is":[129],"open":[130],"source,":[131],"integrated":[132],"holistic":[135],"SANSA":[136],"stack,":[137],"documented":[138],"scala-docs,":[140],"covered":[142],"by":[143],"unit":[144],"tests.":[145],"demonstrates":[147],"its":[148],"scalable":[149],"across":[151],"different":[152],"processing":[153],"power":[154],"configurations":[155],"(hyper-)parameter":[157],"setups":[158],"within":[159],"various":[160],"experiments.":[161],"brings":[164],"three":[166],"worlds":[167],"graph":[170],"engineers,":[171],"computation":[173],"developers,":[174],"scientists":[177],"closer":[178],"together":[179],"all":[182],"them":[184],"creation":[186],"explainable":[188],"ML":[189],"using":[191],"few":[193],"lines":[194],"code.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}