{"id":"https://openalex.org/W4380928489","doi":"https://doi.org/10.1145/3595360.3595853","title":"P2D: A Transpiler Framework for Optimizing Data Science Pipelines","display_name":"P2D: A Transpiler Framework for Optimizing Data Science Pipelines","publication_year":2023,"publication_date":"2023-06-16","ids":{"openalex":"https://openalex.org/W4380928489","doi":"https://doi.org/10.1145/3595360.3595853"},"language":"en","primary_location":{"id":"doi:10.1145/3595360.3595853","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3595360.3595853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092187334","display_name":"Yordan Grigorov","orcid":"https://orcid.org/0009-0000-3350-1555"},"institutions":[{"id":"https://openalex.org/I151281966","display_name":"Cisco Systems (China)","ror":"https://ror.org/02qy75381","country_code":"CN","type":"company","lineage":["https://openalex.org/I135428043","https://openalex.org/I151281966"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yordan Grigorov","raw_affiliation_strings":["Cisco Systems, Sofia, BG"],"affiliations":[{"raw_affiliation_string":"Cisco Systems, Sofia, BG","institution_ids":["https://openalex.org/I151281966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034107370","display_name":"Haralampos Gavriilidis","orcid":"https://orcid.org/0000-0002-3910-5059"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Haralampos Gavriilidis","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Berlin, DE"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Berlin, DE","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033843672","display_name":"Sergey Redyuk","orcid":"https://orcid.org/0000-0001-7131-745X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergey Redyuk","raw_affiliation_strings":["DFKI GmbH, Berlin, DE"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH, Berlin, DE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007094287","display_name":"Kaustubh Beedkar","orcid":"https://orcid.org/0009-0006-2322-4527"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kaustubh Beedkar","raw_affiliation_strings":["Indian Institute of Technology Delhi, New Delhi, IN"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Delhi, New Delhi, IN","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002413906","display_name":"Volker Markl","orcid":"https://orcid.org/0009-0009-0964-026X"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Markl","raw_affiliation_strings":["Technische Universit\u00e4t Berlin, Berlin, DE"],"affiliations":[{"raw_affiliation_string":"Technische Universit\u00e4t Berlin, Berlin, DE","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5092187334"],"corresponding_institution_ids":["https://openalex.org/I151281966"],"apc_list":null,"apc_paid":null,"fwci":0.9075,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.696793,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8353698253631592},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7422380447387695},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6721614599227905},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.6666625142097473},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.6526272296905518},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6206721067428589},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.49035167694091797},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24285250902175903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.10222047567367554}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353698253631592},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7422380447387695},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6721614599227905},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.6666625142097473},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6526272296905518},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6206721067428589},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.49035167694091797},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24285250902175903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.10222047567367554},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595360.3595853","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3595360.3595853","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh Workshop on Data Management for End-to-End Machine Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1970372442","https://openalex.org/W2036971997","https://openalex.org/W2044849727","https://openalex.org/W2102458936","https://openalex.org/W2807799957","https://openalex.org/W2948062280","https://openalex.org/W2962991166","https://openalex.org/W2971290973","https://openalex.org/W3008534594","https://openalex.org/W3082494217","https://openalex.org/W4312701113","https://openalex.org/W4312867851","https://openalex.org/W4385270607"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"transpilation-based":[6],"approach":[7,26,118],"to":[8,28,37,51,61,67,126],"optimize":[9],"data":[10,20,42,53,60,90,105,121],"science":[11,21,43,91,106,122],"pipelines":[12],"that":[13,116],"comprise":[14],"database":[15],"management":[16],"systems":[17],"(DBMSes)":[18],"and":[19,32,93,97,112],"runtimes":[22],"(e.g.,":[23],"Python).":[24],"Our":[25,78,108],"allows":[27,87],"identify":[29],"DBMS-supported":[30],"operations":[31],"translate":[33],"them":[34],"into":[35],"SQL":[36],"leverage":[38],"DBMSes":[39,94],"for":[40,103],"accelerating":[41],"workloads.":[44],"The":[45],"optimization":[46],"target":[47],"is":[48],"twofold:":[49],"First,":[50],"improve":[52],"loading,":[54],"by":[55,72,124],"reducing":[56],"the":[57],"amount":[58],"of":[59,129],"be":[62],"transferred":[63],"between":[64],"runtimes.":[65],"Second,":[66],"exploit":[68],"DBMS":[69],"processing":[70],"capabilities":[71],"\"pushing":[73],"down\"":[74],"certain":[75],"pre-processing":[76],"operations.":[77],"optimizations":[79],"are":[80],"based":[81],"on":[82],"an":[83,127],"intermediate":[84],"representation,":[85],"which":[86],"supporting":[88],"different":[89,104],"libraries":[92],"as":[95],"frontends":[96],"backends":[98],"respectively,":[99],"making":[100],"it":[101],"suitable":[102],"pipelines.":[107],"evaluation":[109],"with":[110],"real-world":[111],"synthetic":[113],"datasets":[114],"shows":[115],"our":[117],"can":[119],"accelerate":[120],"workloads":[123],"up":[125],"order":[128],"magnitude":[130],"over":[131],"state-of-the-art":[132],"approaches.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}