{"id":"https://openalex.org/W4402042785","doi":"https://doi.org/10.14778/3681954.3681984","title":"Efficiently Mitigating the Impact of Data Drift on Machine Learning Pipelines","display_name":"Efficiently Mitigating the Impact of Data Drift on Machine Learning Pipelines","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4402042785","doi":"https://doi.org/10.14778/3681954.3681984"},"language":"en","primary_location":{"id":"doi:10.14778/3681954.3681984","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3681984","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5110626305","display_name":"Sijie Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sijie Dong","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488348","display_name":"Qitong Wang","orcid":"https://orcid.org/0000-0001-6360-3800"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Qitong Wang","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039032451","display_name":"Soror Sahri","orcid":"https://orcid.org/0000-0002-1554-7565"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Soror Sahri","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726723","display_name":"Themis Palpanas","orcid":"https://orcid.org/0000-0002-8031-0265"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Themis Palpanas","raw_affiliation_strings":["Universit\u00e9 Paris Cit\u00e9, Paris, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Paris Cit\u00e9, Paris, France","institution_ids":["https://openalex.org/I204730241"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109772683","display_name":"Divesh Srivastava","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&T, Bedminster, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT&T, Bedminster, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5110626305"],"corresponding_institution_ids":["https://openalex.org/I204730241"],"apc_list":null,"apc_paid":null,"fwci":2.0285,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8859917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"17","issue":"11","first_page":"3072","last_page":"3081"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.9937000274658203,"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/computer-science","display_name":"Computer science","score":0.794370174407959},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.7913353443145752},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.6567855477333069},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6002167463302612},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4843696057796478},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4672650694847107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4455747604370117},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.42276692390441895},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4188336431980133},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4133619964122772},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4116833508014679},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.15734601020812988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794370174407959},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.7913353443145752},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.6567855477333069},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6002167463302612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4843696057796478},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4672650694847107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4455747604370117},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.42276692390441895},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4188336431980133},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4133619964122772},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4116833508014679},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.15734601020812988},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3681954.3681984","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3681954.3681984","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W123476658","https://openalex.org/W1503708763","https://openalex.org/W2022775778","https://openalex.org/W2073768640","https://openalex.org/W2342049278","https://openalex.org/W2402668406","https://openalex.org/W2440722286","https://openalex.org/W2548122763","https://openalex.org/W2559809785","https://openalex.org/W2791425844","https://openalex.org/W2889249015","https://openalex.org/W2954471638","https://openalex.org/W2970143329","https://openalex.org/W2972574632","https://openalex.org/W2979997102","https://openalex.org/W2988437828","https://openalex.org/W2996061341","https://openalex.org/W3029990846","https://openalex.org/W3137125108","https://openalex.org/W3166319166","https://openalex.org/W3175914825","https://openalex.org/W4285260241","https://openalex.org/W6688325169","https://openalex.org/W6888840370"],"related_works":["https://openalex.org/W2081982437","https://openalex.org/W4394857231","https://openalex.org/W2027050655","https://openalex.org/W3028244590","https://openalex.org/W4254349500","https://openalex.org/W2014369232","https://openalex.org/W3122042562","https://openalex.org/W2050078012","https://openalex.org/W2060761133","https://openalex.org/W4399531511"],"abstract_inverted_index":{"Despite":[0],"the":[1,20,56,64,144,157],"increasing":[2],"success":[3],"of":[4,23,97,146,175],"Machine":[5],"Learning":[6],"(ML)":[7],"techniques":[8],"in":[9,85,100,156,173],"real-world":[10],"applications,":[11],"their":[12],"maintenance":[13],"over":[14,38,201],"time":[15],"remains":[16],"challenging.":[17],"In":[18,72,160],"particular,":[19],"prediction":[21,86],"accuracy":[22],"deployed":[24],"ML":[25,57,131,158],"models":[26],"can":[27,105],"suffer":[28],"due":[29],"to":[30,69,83,109,162],"significant":[31],"changes":[32],"between":[33],"training":[34],"and":[35,53,152,190],"serving":[36,101],"data":[37,42,45,80,98,102,147,164],"time,":[39],"known":[40],"as":[41],"drift.":[43],"Traditional":[44],"drift":[46,66,104,148,165],"solutions":[47],"primarily":[48],"focus":[49],"on":[50,138,149,187],"detecting":[51],"drift,":[52],"then":[54,89],"retraining":[55,171],"models,":[58,132,191],"but":[59],"do":[60],"not":[61,78],"discern":[62],"whether":[63],"detected":[65],"is":[67],"harmful":[68,108,176],"model":[70,110,150,170,181],"performance.":[71,182],"this":[73],"paper,":[74],"we":[75,113,141,167],"observe":[76],"that":[77,178,195],"all":[79],"drifts":[81,177],"lead":[82],"degradation":[84],"accuracy.":[87,206],"We":[88],"introduce":[90],"a":[91],"novel":[92],"approach":[93,197],"for":[94,169],"identifying":[95],"portions":[96],"distributions":[99],"where":[103],"be":[106],"potentially":[107],"performance,":[111],"which":[112],"term":[114],"Data":[115],"Distributions":[116],"with":[117],"Low":[118],"Accuracy":[119],"(DDLA).":[120],"Our":[121],"approach,":[122],"using":[123],"decision":[124],"trees,":[125],"precisely":[126],"pinpoints":[127],"low-accuracy":[128],"zones":[129],"within":[130],"especially":[133],"Blackbox":[134],"models.":[135],"By":[136],"focusing":[137],"these":[139],"DDLAs,":[140],"effectively":[142],"assess":[143],"impact":[145],"performance":[151],"make":[153],"informed":[154],"decisions":[155],"pipeline.":[159],"contrast":[161],"existing":[163],"techniques,":[166],"advocate":[168],"only":[172],"cases":[174],"detrimentally":[179],"affect":[180],"Through":[183],"extensive":[184],"experimental":[185],"evaluations":[186],"various":[188],"datasets":[189],"our":[192,196],"findings":[193],"demonstrate":[194],"significantly":[198],"improves":[199],"cost-efficiency":[200],"baselines,":[202],"while":[203],"achieving":[204],"comparable":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}