{"id":"https://openalex.org/W4407355413","doi":"https://doi.org/10.1145/3709705","title":"Modyn: Data-Centric Machine Learning Pipeline Orchestration","display_name":"Modyn: Data-Centric Machine Learning Pipeline Orchestration","publication_year":2025,"publication_date":"2025-02-10","ids":{"openalex":"https://openalex.org/W4407355413","doi":"https://doi.org/10.1145/3709705"},"language":"en","primary_location":{"id":"doi:10.1145/3709705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709705","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3709705","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087722764","display_name":"Maximilian B\u00f6ther","orcid":"https://orcid.org/0000-0003-4093-4361"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Maximilian B\u00f6ther","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-4093-4361","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006238663","display_name":"Ties Robroek","orcid":"https://orcid.org/0009-0006-3451-5602"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ties Robroek","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0009-0006-3451-5602","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040922950","display_name":"Viktor Gsteiger","orcid":"https://orcid.org/0000-0002-6750-5500"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Viktor Gsteiger","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-6750-5500","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057498231","display_name":"R Holzinger","orcid":"https://orcid.org/0000-0002-7505-0673"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Robin Holzinger","raw_affiliation_strings":["Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-7505-0673","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095776589","display_name":"Xianzhe Ma","orcid":"https://orcid.org/0009-0000-1400-6735"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Xianzhe Ma","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0000-1400-6735","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061990490","display_name":"P\u0131nar T\u00f6z\u00fcn","orcid":"https://orcid.org/0000-0001-6838-4854"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"P\u0131nar T\u00f6z\u00fcn","raw_affiliation_strings":["IT University of Copenhagen, Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0001-6838-4854","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000009841","display_name":"Ana Klimovic","orcid":"https://orcid.org/0000-0001-8559-0529"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ana Klimovic","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-8559-0529","affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94589496,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"3","issue":"1","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","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/T12761","display_name":"Data Stream Mining Techniques","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/T12535","display_name":"Machine Learning and Data Classification","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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.8892513513565063},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7582621574401855},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.59739089012146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.390686959028244},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3254055976867676},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3236677050590515},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1286669373512268},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.04698699712753296}],"concepts":[{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.8892513513565063},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7582621574401855},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.59739089012146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.390686959028244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3254055976867676},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3236677050590515},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1286669373512268},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.04698699712753296},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3709705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709705","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/3c4867ca-0f54-4916-93c9-ee174f2843d9","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/3c4867ca-0f54-4916-93c9-ee174f2843d9","pdf_url":"https://www.mboether.com/assets/pdf/bother2025modyn.pdf","source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"B\u00f6ther, M, Robroek, T T, Gsteiger, V, Holzinger, R, Ma, X, T\u00f6z\u00fcn, P & Klimovic, A 2025, 'Modyn: Data-Centric Machine Learning Pipeline Orchestration', Proc. ACM Manag. Data, vol. 3, no. 1, pp. 1-30. https://doi.org/10.1145/3709705","raw_type":"article"},{"id":"pmh:doi:10.3929/ethz-c-000793195","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/793195","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1145/3709705","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3709705","pdf_url":null,"source":{"id":"https://openalex.org/S4387289859","display_name":"Proceedings of the ACM on Management of Data","issn_l":"2836-6573","issn":["2836-6573"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Management of Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G971243675","display_name":null,"funder_award_id":"200021_204620","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W2069701377","https://openalex.org/W2072627547","https://openalex.org/W2076618162","https://openalex.org/W2103753221","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2157103390","https://openalex.org/W2194775991","https://openalex.org/W2542459869","https://openalex.org/W2743948853","https://openalex.org/W2794670651","https://openalex.org/W2795903893","https://openalex.org/W2889249015","https://openalex.org/W2893890695","https://openalex.org/W2898017895","https://openalex.org/W2921243078","https://openalex.org/W2947737663","https://openalex.org/W2954929116","https://openalex.org/W2966284335","https://openalex.org/W3008570669","https://openalex.org/W3013082216","https://openalex.org/W3029990846","https://openalex.org/W3035305184","https://openalex.org/W3036963153","https://openalex.org/W3045754299","https://openalex.org/W3103438889","https://openalex.org/W3104128335","https://openalex.org/W3105684693","https://openalex.org/W3132433578","https://openalex.org/W3154155772","https://openalex.org/W3166319166","https://openalex.org/W3168149265","https://openalex.org/W3179411055","https://openalex.org/W3187308167","https://openalex.org/W3192495122","https://openalex.org/W3193974325","https://openalex.org/W3196732841","https://openalex.org/W3197720002","https://openalex.org/W3200211247","https://openalex.org/W3203313709","https://openalex.org/W3206742286","https://openalex.org/W4281487149","https://openalex.org/W4281657584","https://openalex.org/W4285605356","https://openalex.org/W4297808460","https://openalex.org/W4316126954","https://openalex.org/W4317641499","https://openalex.org/W4367310586","https://openalex.org/W4368353258","https://openalex.org/W4376988885","https://openalex.org/W4379390538","https://openalex.org/W4380433165","https://openalex.org/W4381328970","https://openalex.org/W4384616255","https://openalex.org/W4386065403","https://openalex.org/W4386841375","https://openalex.org/W4387846512","https://openalex.org/W4388041017","https://openalex.org/W4388788849","https://openalex.org/W4389364022","https://openalex.org/W4390872468","https://openalex.org/W4391915405","https://openalex.org/W4393213638","https://openalex.org/W4394666024","https://openalex.org/W4400604939","https://openalex.org/W6688325169","https://openalex.org/W6910963612","https://openalex.org/W6948537149"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"In":[0],"real-world":[1],"machine":[2,66],"learning":[3,67],"(ML)":[4],"pipelines,":[5],"datasets":[6],"are":[7],"continuously":[8,80],"growing.":[9],"Models":[10],"must":[11],"incorporate":[12],"this":[13],"new":[14],"training":[15,81,120,188],"data":[16,43,94,102,162,172,191],"to":[17,22,33,75,92,141],"improve":[18],"generalization":[19],"and":[20,40,104,115,126,135,164,174,180],"adapt":[21],"potential":[23],"distribution":[24],"shifts.":[25],"The":[26,122],"cost":[27],"of":[28,53,101,111,131,145,152,158],"model":[29,37,83,178],"retraining":[30,54],"is":[31,38,45,124],"proportional":[32],"how":[34,41,140,170],"frequently":[35],"the":[36,50,99,109,143,150],"retrained":[39],"much":[42],"it":[44],"trained":[46],"on,":[47],"which":[48],"makes":[49],"naive":[51],"approach":[52],"from":[55],"scratch":[56],"each":[57],"time":[58],"impractical.":[59],"We":[60,137,167],"present":[61],"Modyn,":[62],"a":[63,82,85],"data-centric":[64],"end-to-end":[65],"platform.":[68],"Modyn's":[69],"ML":[70,119,146],"pipeline":[71],"abstraction":[72],"enables":[73,185],"users":[74,91],"declaratively":[76],"describe":[77],"policies":[78,96,106,176],"for":[79],"on":[84],"growing":[86],"dataset.":[87],"Modyn":[88,113,184],"pipelines":[89,147,159],"allow":[90],"apply":[93],"selection":[95,163,173],"(to":[97,107],"reduce":[98,108],"number":[100,110],"points)":[103],"triggering":[105,165,175],"trainings).":[112],"executes":[114],"orchestrates":[116],"these":[117],"continuous":[118],"pipelines.":[121],"system":[123],"open-source":[125],"comes":[127],"with":[128,160,189],"an":[129],"ecosystem":[130],"benchmark":[132],"datasets,":[133],"models,":[134,154],"tooling.":[136],"formally":[138],"discuss":[139],"measure":[142],"performance":[144],"by":[148],"introducing":[149],"concept":[151],"composite":[153],"enabling":[155],"fair":[156],"comparison":[157],"different":[161],"policies.":[166],"empirically":[168],"analyze":[169],"various":[171],"impact":[177],"accuracy,":[179],"also":[181],"show":[182],"that":[183],"high":[186],"throughput":[187],"sample-level":[190],"selection.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}