{"id":"https://openalex.org/W4311113370","doi":"https://doi.org/10.48550/arxiv.2111.12490","title":"Matching Learned Causal Effects of Neural Networks with Domain Priors","display_name":"Matching Learned Causal Effects of Neural Networks with Domain Priors","publication_year":2021,"publication_date":"2021-11-24","ids":{"openalex":"https://openalex.org/W4311113370","doi":"https://doi.org/10.48550/arxiv.2111.12490"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2111.12490","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.12490","pdf_url":"https://arxiv.org/pdf/2111.12490","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2111.12490","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019014249","display_name":"Sai Srinivas Kancheti","orcid":"https://orcid.org/0000-0001-9300-7209","observed_orcids":["https://orcid.org/0000-0001-9300-7209"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kancheti, Sai Srinivas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035298151","display_name":"Abbavaram Gowtham Reddy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reddy, Abbavaram Gowtham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038020125","display_name":"Vineeth Nallure Balasubramanian","orcid":"https://orcid.org/0000-0003-2656-0375","observed_orcids":["https://orcid.org/0000-0003-2656-0375"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balasubramanian, Vineeth N","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080592530","display_name":"Amit Kumar Sharma","orcid":"https://orcid.org/0000-0003-1451-5892","observed_orcids":["https://orcid.org/0000-0003-1451-5892"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Amit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8179000020027161,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8179000020027161,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.08510000258684158,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.05169999971985817,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/structural-causal-models","display_name":"structural causal models","score":0.8880000114440918},{"id":"https://openalex.org/keywords/neural-network","display_name":"artificial neural networks","score":0.7490000128746033},{"id":"https://openalex.org/keywords/monotonicity-constraints","display_name":"monotonicity constraints","score":0.8259999752044678},{"id":"https://openalex.org/keywords/fairness","display_name":"fairness","score":0.7559999823570251},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.8243374228477478},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.7343578934669495},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6357784271240234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6188051700592041},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5905486345291138},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.5612016320228577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5437139868736267},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5293263792991638},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5096268653869629},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5011105537414551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4885614812374115},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.47500717639923096},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4176701605319977},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3303045332431793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24639713764190674},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.14761829376220703},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1251946985721588},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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":2,"locations":[{"id":"pmh:oai:arXiv.org:2111.12490","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.12490","pdf_url":"https://arxiv.org/pdf/2111.12490","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2111.12490","doi":"https://doi.org/10.48550/arxiv.2111.12490","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2111.12490","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2111.12490","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.12490","pdf_url":"https://arxiv.org/pdf/2111.12490","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3215662296","https://openalex.org/W6931628601","https://openalex.org/W4389217362","https://openalex.org/W2752625228","https://openalex.org/W3180438404","https://openalex.org/W4393160173","https://openalex.org/W4402594840","https://openalex.org/W3037834521","https://openalex.org/W3098573462","https://openalex.org/W7124175540"],"abstract_inverted_index":{"A":[0],"trained":[1,172],"neural":[2,91,152],"network":[3,92,153],"can":[4,108],"be":[5],"interpreted":[6],"as":[7],"a":[8,35,80,90,132,151,169],"structural":[9],"causal":[10,31,47,66,87,101,119,129,158],"model":[11,36,154,170],"(SCM)":[12],"that":[13,37,83,105,168],"provides":[14],"the":[15,22,45,55,65,85],"effect":[16,120,130],"of":[17,64,89,113,118,121,131,138],"changing":[18],"input":[19,50,70,123],"variables":[20,71],"on":[21,125,134,142,162,179],"model's":[23],"output.":[24],"However,":[25],"if":[26],"training":[27],"data":[28],"contains":[29],"both":[30,97],"and":[32,51,72,99,175],"correlational":[33],"relationships,":[34],"optimizes":[38],"prediction":[39],"accuracy":[40,178],"may":[41],"not":[42],"necessarily":[43],"learn":[44],"true":[46],"relationships":[48],"between":[49,68],"output":[52,73,126,135],"variables.":[53],"On":[54],"other":[56],"hand,":[57],"expert":[58],"users":[59],"often":[60],"have":[61],"prior":[62],"knowledge":[63],"relationship":[67],"certain":[69],"from":[74],"domain":[75,94,114],"knowledge.":[76],"Therefore,":[77],"we":[78,165],"propose":[79],"regularization":[81],"method":[82],"aligns":[84],"learned":[86],"effects":[88],"with":[93],"priors,":[95,115],"including":[96,116],"direct":[98],"total":[100],"effects.":[102],"We":[103],"show":[104,146,167],"this":[106],"approach":[107],"generalize":[109],"to":[110,155],"different":[111],"kinds":[112],"monotonicity":[117],"an":[122],"variable":[124,133],"or":[127],"zero":[128],"for":[136],"purposes":[137],"fairness.":[139],"Our":[140],"experiments":[141],"twelve":[143],"benchmark":[144],"datasets":[145],"its":[147],"utility":[148],"in":[149],"regularizing":[150],"maintain":[156],"desired":[157],"effects,":[159],"without":[160],"compromising":[161],"accuracy.":[163],"Importantly,":[164],"also":[166],"thus":[171],"is":[173],"robust":[174],"gets":[176],"improved":[177],"noisy":[180],"inputs.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2022-12-23T00:00:00"}