{"id":"https://openalex.org/W4282038795","doi":"https://doi.org/10.1145/3514221.3517849","title":"Complaint-Driven Training Data Debugging at Interactive Speeds","display_name":"Complaint-Driven Training Data Debugging at Interactive Speeds","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4282038795","doi":"https://doi.org/10.1145/3514221.3517849"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517849","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003070287","display_name":"Lampros Flokas","orcid":"https://orcid.org/0000-0002-2496-3624"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lampros Flokas","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019002958","display_name":"Weiyuan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Weiyuan Wu","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077085197","display_name":"Yejia Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yejia Liu","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019307205","display_name":"Nakul Verma","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nakul Verma","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049016095","display_name":"Eugene Wu","orcid":"https://orcid.org/0000-0003-4254-6688"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene Wu","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"369","last_page":"383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9965000152587891,"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":0.9797000288963318,"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":0.802733302116394},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.7895530462265015},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5882374048233032},{"id":"https://openalex.org/keywords/complaint","display_name":"Complaint","score":0.5656108856201172},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.42387765645980835},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.41631942987442017},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41065263748168945},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3714761435985565},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3576422333717346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34434375166893005},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30642935633659363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.802733302116394},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.7895530462265015},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5882374048233032},{"id":"https://openalex.org/C2780838233","wikidata":"https://www.wikidata.org/wiki/Q836925","display_name":"Complaint","level":2,"score":0.5656108856201172},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.42387765645980835},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41631942987442017},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41065263748168945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3714761435985565},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3576422333717346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34434375166893005},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30642935633659363},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3517849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517849","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2396607283","display_name":null,"funder_award_id":"1845638,2008295,2106197,2103794","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1971781829","https://openalex.org/W1974627246","https://openalex.org/W2000809552","https://openalex.org/W2002544066","https://openalex.org/W2004026774","https://openalex.org/W2044849727","https://openalex.org/W2047182010","https://openalex.org/W2048864522","https://openalex.org/W2070664725","https://openalex.org/W2117470435","https://openalex.org/W2129815685","https://openalex.org/W2143102052","https://openalex.org/W2282821441","https://openalex.org/W2293299776","https://openalex.org/W2316564661","https://openalex.org/W2889249015","https://openalex.org/W2917161856","https://openalex.org/W2930957955","https://openalex.org/W2948985893","https://openalex.org/W2999905431","https://openalex.org/W3008570669","https://openalex.org/W3015276915","https://openalex.org/W3041133507","https://openalex.org/W3095119922","https://openalex.org/W3103264664","https://openalex.org/W3103438889","https://openalex.org/W3176502563","https://openalex.org/W4235797544","https://openalex.org/W4237456942","https://openalex.org/W6601211009"],"related_works":["https://openalex.org/W1885497808","https://openalex.org/W4389612504","https://openalex.org/W2022249118","https://openalex.org/W51147162","https://openalex.org/W3009921285","https://openalex.org/W2046737675","https://openalex.org/W1596393722","https://openalex.org/W2072761933","https://openalex.org/W4327644547","https://openalex.org/W2061417947"],"abstract_inverted_index":{"Modern":[0],"databases":[1],"support":[2],"queries":[3,16,49,205],"that":[4,56,149,160],"perform":[5],"model":[6,24,114,134,189],"inference":[7,15,48],"(inference":[8],"queries).":[9],"Although":[10,99],"powerful":[11],"and":[12,69,107,113,159,202],"widely":[13],"used,":[14],"are":[17,109,154,163],"susceptible":[18],"to":[19,28,51,90,117,143,176,179,183],"incorrect":[20],"results":[21,68],"if":[22],"the":[23,45,60,78,87,92,101,110,121,157,196],"is":[25,103,199],"biased":[26],"due":[27,116],"training":[29,54,71,97,111],"data":[30,38,177],"errors.":[31],"Recently,":[32],"prior":[33],"work":[34],"Rain":[35,73],"proposed":[36],"complaint-driven":[37],"debugging":[39,152,181,216],"which":[40],"uses":[41,168],"user-specified":[42],"errors":[43],"in":[44,212],"output":[46],"of":[47,94,156,188,223],"(Complaints)":[50],"rank":[52],"erroneous":[53],"examples":[55],"most":[57,150],"likely":[58],"caused":[59],"complaint.":[61,146],"This":[62],"can":[63],"help":[64],"users":[65],"better":[66],"interpret":[67],"debug":[70,144],"sets.":[72],"combined":[74],"influence":[75],"analysis":[76],"from":[77,86],"ML":[79],"literature":[80,89],"with":[81,135,221],"relaxed":[82],"query":[83],"provenance":[84],"polynomials":[85],"DB":[88],"approximate":[91],"derivative":[93],"complaints":[95],"w.r.t.":[96],"examples.":[98],"effective,":[100],"runtime":[102],"O(|T|d),":[104],"where":[105],"T":[106],"d":[108],"set":[112],"sizes,":[115],"its":[118],"reliance":[119],"on":[120,172,219],"model's":[122],"second":[123],"order":[124],"derivatives":[125],"(the":[126],"Hessian).":[127],"On":[128],"a":[129,145,184],"Wide":[130],"Resnet":[131],"Network":[132],"(WRN)":[133],"1.5":[136],"million":[137],"parameters,":[138],"it":[139],"takes":[140],">1":[141],"minute":[142],"We":[147,191],"observe":[148],"complaint":[151],"costs":[153],"independent":[155,187],"complaint,":[158],"modern":[161],"models":[162,220],"overparameterized.":[164],"In":[165],"response,":[166],"Rain++":[167,213],"precomputation":[169],"techniques,":[170],"based":[171],"non-trivial":[173],"insights":[174],"unique":[175],"debugging,":[178],"reduce":[180],"latencies":[182,217],"constant":[185],"factor":[186],"size.":[190],"also":[192],"develop":[193],"optimizations":[194,211],"when":[195],"queried":[197],"database":[198],"known":[200],"apriori,":[201],"for":[203],"standing":[204],"over":[206],"streaming":[207],"databases.":[208],"Combining":[209],"these":[210],"ensures":[214],"interactive":[215],"(~1ms)":[218],"millions":[222],"parameters.":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}