{"id":"https://openalex.org/W2613873989","doi":"https://doi.org/10.1145/3070607.3070612","title":"Benchmarking Data Flow Systems for Scalable Machine Learning","display_name":"Benchmarking Data Flow Systems for Scalable Machine Learning","publication_year":2017,"publication_date":"2017-05-08","ids":{"openalex":"https://openalex.org/W2613873989","doi":"https://doi.org/10.1145/3070607.3070612","mag":"2613873989"},"language":"en","primary_location":{"id":"doi:10.1145/3070607.3070612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3070607.3070612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and Beyond","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/A5030302319","display_name":"Christoph Boden","orcid":null},"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":"Christoph Boden","raw_affiliation_strings":["TU Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039495925","display_name":"Andr\u00e9a P. Spina","orcid":null},"institutions":[{"id":"https://openalex.org/I2800373336","display_name":"Radiall (France)","ror":"https://ror.org/0122jkj38","country_code":"FR","type":"company","lineage":["https://openalex.org/I2800373336"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Andrea Spina","raw_affiliation_strings":["TU Berlin and Radicalbit S.r.l"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Berlin and Radicalbit S.r.l","institution_ids":["https://openalex.org/I2800373336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002030730","display_name":"Tilmann Rabl","orcid":"https://orcid.org/0009-0009-3335-8045"},"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":"Tilmann Rabl","raw_affiliation_strings":["TU Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]},{"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":["TU Berlin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Berlin","institution_ids":["https://openalex.org/I4577782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2719,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90847803,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9984999895095825,"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":0.9980999827384949,"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":0.8435204029083252},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8362011313438416},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8236879706382751},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7242698073387146},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5288235545158386},{"id":"https://openalex.org/keywords/sort","display_name":"sort","score":0.5211301445960999},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45488834381103516},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4414959251880646},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4151468276977539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41273078322410583},{"id":"https://openalex.org/keywords/data-flow-diagram","display_name":"Data flow diagram","score":0.4124959707260132},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40851548314094543},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3817344307899475},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35072752833366394},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3131842315196991},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13154929876327515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8435204029083252},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8362011313438416},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8236879706382751},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7242698073387146},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5288235545158386},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.5211301445960999},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45488834381103516},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4414959251880646},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4151468276977539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41273078322410583},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.4124959707260132},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40851548314094543},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3817344307899475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35072752833366394},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3131842315196991},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13154929876327515},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3070607.3070612","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3070607.3070612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM SIGMOD Workshop on Algorithms and Systems for MapReduce and Beyond","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":0.6100000143051147}],"awards":[{"id":"https://openalex.org/G4836120834","display_name":null,"funder_award_id":"01IS14013A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1425731158","https://openalex.org/W1542014621","https://openalex.org/W1979382551","https://openalex.org/W2016653720","https://openalex.org/W2029237784","https://openalex.org/W2029463952","https://openalex.org/W2051434435","https://openalex.org/W2074694452","https://openalex.org/W2083842231","https://openalex.org/W2090883204","https://openalex.org/W2103018059","https://openalex.org/W2109664771","https://openalex.org/W2121810937","https://openalex.org/W2131975293","https://openalex.org/W2146620757","https://openalex.org/W2173213060","https://openalex.org/W2190012392","https://openalex.org/W2357449897","https://openalex.org/W2498111289","https://openalex.org/W2566979091","https://openalex.org/W2584112163","https://openalex.org/W2951781666","https://openalex.org/W6676373471"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2011676020","https://openalex.org/W2000169967"],"abstract_inverted_index":{"Distributed":[0],"data":[1,40,57,83],"flow":[2,58],"systems":[3,59],"such":[4,28,60,70],"as":[5,29,61,71],"Apache":[6,9,62],"Spark":[7,64],"or":[8,65,74],"Flink":[10],"are":[11,43],"popular":[12],"choices":[13],"for":[14],"scaling":[15],"machine":[16,26],"learning":[17,27],"algorithms":[18],"in":[19],"production.":[20],"Industry":[21],"applications":[22],"of":[23,39,56,93],"large":[24],"scale":[25],"click-through":[30],"rate":[31],"prediction":[32],"rely":[33],"on":[34,37],"models":[35],"trained":[36],"billions":[38],"points":[41],"which":[42],"both":[44],"highly":[45],"sparse":[46],"and":[47,86],"high-dimensional.":[48],"Existing":[49],"Benchmarks":[50],"attempt":[51],"to":[52,82,88],"assess":[53],"the":[54,90],"performance":[55],"Flink,":[63],"Hadoop":[66],"with":[67,80],"non-representative":[68],"workloads":[69],"WordCount,":[72],"Grep":[73],"Sort.":[75],"They":[76],"only":[77],"evaluate":[78],"scalability":[79],"respect":[81],"set":[84],"size":[85],"fail":[87],"address":[89],"crucial":[91],"requirement":[92],"handling":[94],"high":[95],"dimensional":[96],"data.":[97]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}