{"id":"https://openalex.org/W3210561222","doi":"https://doi.org/10.1145/3459637.3482380","title":"Pulling Up by the Causal Bootstraps","display_name":"Pulling Up by the Causal Bootstraps","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3210561222","doi":"https://doi.org/10.1145/3459637.3482380","mag":"3210561222"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459637.3482380","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459637.3482380","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3459637.3482380","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019357628","display_name":"Sindhu C. M. Gowda","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Sindhu C. M. Gowda","raw_affiliation_strings":["University of Toronto & Vector Institute, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto & Vector Institute, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035149567","display_name":"Shalmali Joshi","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shalmali Joshi","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340498","display_name":"Haoran Zhang","orcid":"https://orcid.org/0000-0003-1027-9976"},"institutions":[{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Haoran Zhang","raw_affiliation_strings":["University of Toronto & Vector Institute, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto & Vector Institute, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070063054","display_name":"Marzyeh Ghassemi","orcid":"https://orcid.org/0000-0001-6349-7251"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marzyeh Ghassemi","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019357628"],"corresponding_institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65235844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"606","last_page":"616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9986000061035156,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7799861431121826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7103226184844971},{"id":"https://openalex.org/keywords/debiasing","display_name":"Debiasing","score":0.7007756233215332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6316226720809937},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6156061291694641},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.5011961460113525},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.4721496105194092},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4574398994445801},{"id":"https://openalex.org/keywords/causation","display_name":"Causation","score":0.45232850313186646},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.42969390749931335},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3435940146446228},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.24221175909042358},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10684385895729065},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09915590286254883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7799861431121826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7103226184844971},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.7007756233215332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6316226720809937},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6156061291694641},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.5011961460113525},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.4721496105194092},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4574398994445801},{"id":"https://openalex.org/C166151441","wikidata":"https://www.wikidata.org/wiki/Q4923601","display_name":"Causation","level":2,"score":0.45232850313186646},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.42969390749931335},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3435940146446228},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.24221175909042358},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10684385895729065},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09915590286254883},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.0},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3459637.3482380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459637.3482380","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459637.3482380","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2108.12510","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.12510","pdf_url":"https://arxiv.org/pdf/2108.12510","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3459637.3482380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3459637.3482380","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3459637.3482380","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3033334534","display_name":null,"funder_award_id":"AI Chair","funder_id":"https://openalex.org/F4320309949","funder_display_name":"Canadian Institute for Advanced Research"},{"id":"https://openalex.org/G5784215521","display_name":null,"funder_award_id":"Chair","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320319880","display_name":"Government of Canada","ror":"https://ror.org/010q4q527"},{"id":"https://openalex.org/F4320330223","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3210561222.pdf","grobid_xml":"https://content.openalex.org/works/W3210561222.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1486066286","https://openalex.org/W1537314526","https://openalex.org/W1834627138","https://openalex.org/W1978380814","https://openalex.org/W2030498706","https://openalex.org/W2049910836","https://openalex.org/W2111355007","https://openalex.org/W2131953535","https://openalex.org/W2134067266","https://openalex.org/W2143891888","https://openalex.org/W2162670686","https://openalex.org/W2557738935","https://openalex.org/W2581082771","https://openalex.org/W2611650229","https://openalex.org/W2740962769","https://openalex.org/W2788557041","https://openalex.org/W2882983190","https://openalex.org/W2883386984","https://openalex.org/W2887175137","https://openalex.org/W2937229771","https://openalex.org/W2952428244","https://openalex.org/W2963350032","https://openalex.org/W2963453204","https://openalex.org/W2963466845","https://openalex.org/W2963608118","https://openalex.org/W2965628639","https://openalex.org/W2971274354","https://openalex.org/W2981869278","https://openalex.org/W2990751682","https://openalex.org/W2995225687","https://openalex.org/W3005040148","https://openalex.org/W3009845780","https://openalex.org/W3011762034","https://openalex.org/W3011967257","https://openalex.org/W3027716283","https://openalex.org/W3035037113","https://openalex.org/W3041475347","https://openalex.org/W3101156210","https://openalex.org/W4220820301","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4253624503","https://openalex.org/W4388356905","https://openalex.org/W4255808401","https://openalex.org/W3215034539","https://openalex.org/W4313422683","https://openalex.org/W4282978140","https://openalex.org/W2894915327","https://openalex.org/W2161504683","https://openalex.org/W173644421","https://openalex.org/W2951813053"],"abstract_inverted_index":{"Machine":[0],"learning":[1,9,79,125],"models":[2,17,47],"achieve":[3],"state-of-the-art":[4],"performance":[5],"on":[6,22,123,133,162],"many":[7],"supervised":[8],"tasks.":[10,167],"However,":[11],"prior":[12],"evidence":[13],"suggests":[14],"that":[15,30,146],"these":[16,113,137],"may":[18],"learn":[19],"to":[20,54,68,131,158,189,193],"rely":[21,132],"\"shortcut\"":[23],"biases":[24,135,138],"or":[25],"spurious":[26],"correlations":[27,29],"(intuitively,":[28],"do":[31],"not":[32,140],"hold":[33,39],"in":[34,40,51],"the":[35,60,71,118,172,177],"test":[36],"as":[37],"they":[38],"train)":[41],"for":[42,176],"good":[43],"predictive":[44],"performance.":[45],"Such":[46],"cannot":[48],"be":[49,69],"trusted":[50],"deployment":[52],"environments":[53],"provide":[55],"accurate":[56],"predictions.":[57],"While":[58],"viewing":[59],"problem":[61],"from":[62],"a":[63,92,148,186],"causal":[64,93,98,149,187],"lens":[65],"is":[66],"known":[67,108],"useful,":[70],"seamless":[72],"integration":[73],"of":[74,120,174],"causation":[75],"techniques":[76],"into":[77],"machine":[78],"pipelines":[80,184],"remains":[81],"cumbersome":[82],"and":[83,90,109,181],"expensive.":[84],"In":[85],"this":[86],"work,":[87],"we":[88,115],"study":[89],"extend":[91],"pre-training":[94,150],"debiasing":[95],"technique":[96,151],"called":[97],"bootstrapping":[99],"(CB)":[100],"under":[101],"five":[102],"practical":[103],"confounded-data":[104],"generation-acquisition":[105],"scenarios":[106],"(with":[107],"unknown":[110],"confounding).":[111],"Under":[112],"settings,":[114],"systematically":[116],"investigate":[117],"effect":[119],"confounding":[121,160,194],"bias":[122,161],"deep":[124],"model":[126],"performance,":[127],"demonstrating":[128],"their":[129],"propensity":[130],"shortcut":[134],"when":[136],"are":[139],"properly":[141],"accounted":[142],"for.":[143],"We":[144],"demonstrate":[145],"such":[147],"can":[152],"significantly":[153],"outperform":[154],"existing":[155],"base":[156],"practices":[157],"mitigate":[159],"real-world":[163],"domain":[164],"generalization":[165],"benchmarking":[166],"This":[168],"systematic":[169],"investigation":[170],"underlines":[171],"importance":[173],"accounting":[175],"underlying":[178],"data-generating":[179],"mechanisms":[180],"fortifying":[182],"data-preprocessing":[183],"with":[185],"framework":[188],"develop":[190],"methods":[191],"robust":[192],"biases.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2021-11-08T00:00:00"}