{"id":"https://openalex.org/W3171322015","doi":"https://doi.org/10.1145/3447548.3467453","title":"How Interpretable and Trustworthy are GAMs?","display_name":"How Interpretable and Trustworthy are GAMs?","publication_year":2021,"publication_date":"2021-08-12","ids":{"openalex":"https://openalex.org/W3171322015","doi":"https://doi.org/10.1145/3447548.3467453","mag":"3171322015"},"language":"en","primary_location":{"id":"doi:10.1145/3447548.3467453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-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/A5104048655","display_name":"Chun\u2010Hao Chang","orcid":"https://orcid.org/0000-0002-6009-6521"},"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"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Chun-Hao Chang","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101755049","display_name":"Sarah Tan","orcid":"https://orcid.org/0000-0001-5453-4874"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Tan","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016470513","display_name":"Ben Lengerich","orcid":null},"institutions":[{"id":"https://openalex.org/I107606265","display_name":"Broad Institute","ror":"https://ror.org/05a0ya142","country_code":"US","type":"funder","lineage":["https://openalex.org/I107606265"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Lengerich","raw_affiliation_strings":["MIT, Broad Institute, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"MIT, Broad Institute, Boston, MA, USA","institution_ids":["https://openalex.org/I107606265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087983309","display_name":"Anna Goldenberg","orcid":"https://orcid.org/0000-0002-2416-833X"},"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":"Anna Goldenberg","raw_affiliation_strings":["University of Toronto, Vector Institute, Hospital of Sick Children, Toronto, ON, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Vector Institute, Hospital of Sick Children, Toronto, ON, Canada","institution_ids":["https://openalex.org/I4210127509","https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083893060","display_name":"Rich Caruana","orcid":"https://orcid.org/0000-0002-6383-7786"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rich Caruana","raw_affiliation_strings":["Microsoft Research, Seattle, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Seattle, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104048655"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":5.1671,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96183836,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9919999837875366,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9918000102043152,"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/fidelity","display_name":"Fidelity","score":0.7566839456558228},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.7444700598716736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7224205136299133},{"id":"https://openalex.org/keywords/generalized-additive-model","display_name":"Generalized additive model","score":0.6513727903366089},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6363480091094971},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.6188254356384277},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5962687730789185},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5678600668907166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.552828311920166},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5492931008338928},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44942614436149597},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3342511057853699},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14439618587493896},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07062563300132751}],"concepts":[{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.7566839456558228},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.7444700598716736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7224205136299133},{"id":"https://openalex.org/C194648359","wikidata":"https://www.wikidata.org/wiki/Q3318054","display_name":"Generalized additive model","level":2,"score":0.6513727903366089},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6363480091094971},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6188254356384277},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5962687730789185},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5678600668907166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.552828311920166},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5492931008338928},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44942614436149597},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3342511057853699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14439618587493896},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07062563300132751},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3447548.3467453","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447548.3467453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1483994939","https://openalex.org/W1596493414","https://openalex.org/W1875061881","https://openalex.org/W1996796871","https://openalex.org/W2090158884","https://openalex.org/W2107624415","https://openalex.org/W2119160928","https://openalex.org/W2135046866","https://openalex.org/W2140514146","https://openalex.org/W2149033360","https://openalex.org/W2171033594","https://openalex.org/W2295598076","https://openalex.org/W2516809705","https://openalex.org/W2543851953","https://openalex.org/W2618851150","https://openalex.org/W2795673246","https://openalex.org/W2798075234","https://openalex.org/W2901070617","https://openalex.org/W2914279003","https://openalex.org/W2947802409","https://openalex.org/W2962790223","https://openalex.org/W2965791769","https://openalex.org/W3005086430","https://openalex.org/W3102476541","https://openalex.org/W3104310207","https://openalex.org/W3112717819","https://openalex.org/W3119576574","https://openalex.org/W3120740533","https://openalex.org/W4233560477","https://openalex.org/W4289097366","https://openalex.org/W4298876635","https://openalex.org/W6832792489","https://openalex.org/W6948711839"],"related_works":["https://openalex.org/W2381850946","https://openalex.org/W4380449851","https://openalex.org/W3125091513","https://openalex.org/W4318832338","https://openalex.org/W2076536433","https://openalex.org/W90316445","https://openalex.org/W4248383205","https://openalex.org/W4234745530","https://openalex.org/W2146383839","https://openalex.org/W2231829109"],"abstract_inverted_index":{"Generalized":[0],"additive":[1],"models":[2,99],"(GAMs)":[3],"have":[4],"become":[5],"a":[6,48,68,93],"leading":[7],"model":[8],"class":[9],"for":[10,19],"interpretable":[11,98],"machine":[12],"learning.":[13],"However,":[14],"there":[15],"are":[16],"many":[17],"algorithms":[18,52],"training":[20],"GAMs,":[21],"and":[22,45,55,80,101,112,114],"these":[23],"can":[24,74],"learn":[25,100],"different":[26],"or":[27],"even":[28],"contradictory":[29],"models,":[30],"while":[31],"being":[32],"equally":[33],"accurate.":[34],"Which":[35],"GAM":[36,51,122],"should":[37],"we":[38,43],"trust?":[39],"In":[40],"this":[41],"paper,":[42],"quantitatively":[44],"qualitatively":[46],"investigate":[47],"variety":[49],"of":[50,109],"on":[53],"real":[54],"simulated":[56],"datasets.":[57],"We":[58],"find":[59],"that":[60,89,102],"GAMs":[61,104],"with":[62],"high":[63],"feature":[64],"sparsity":[65],"(only":[66],"using":[67],"few":[69],"variables":[70],"to":[71,83,117],"make":[72],"predictions)":[73],"miss":[75],"patterns":[76],"in":[77,96],"the":[78,106,119],"data":[79],"be":[81,118],"unfair":[82],"rare":[84],"subpopulations.":[85],"Our":[86],"results":[87],"suggest":[88],"inductive":[90],"bias":[91],"plays":[92],"crucial":[94],"role":[95],"what":[97],"tree-based":[103],"represent":[105],"best":[107],"balance":[108],"sparsity,":[110],"fidelity":[111],"accuracy":[113],"thus":[115],"appear":[116],"most":[120],"trustworthy":[121],"models.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}