{"id":"https://openalex.org/W4394597225","doi":"https://doi.org/10.1109/wacv57701.2024.00443","title":"An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification","display_name":"An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4394597225","doi":"https://doi.org/10.1109/wacv57701.2024.00443"},"language":"en","primary_location":{"id":"doi:10.1109/wacv57701.2024.00443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5002855697","display_name":"Prakhar Ganesh","orcid":"https://orcid.org/0000-0001-8695-4128"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Prakhar Ganesh","raw_affiliation_strings":["Mila, Quebec AI Insitute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila, Quebec AI Insitute","institution_ids":["https://openalex.org/I4210164802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002855697"],"corresponding_institution_ids":["https://openalex.org/I4210164802"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4476","last_page":"4485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8865000009536743,"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":0.8865000009536743,"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/benchmarking","display_name":"Benchmarking","score":0.8367388844490051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6930010318756104},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.6684906482696533},{"id":"https://openalex.org/keywords/multiplicity","display_name":"Multiplicity (mathematics)","score":0.5277208685874939},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.522363007068634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49126094579696655},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4173858165740967},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11903917789459229},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08146652579307556},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0729951560497284}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8367388844490051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6930010318756104},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.6684906482696533},{"id":"https://openalex.org/C156004811","wikidata":"https://www.wikidata.org/wiki/Q2228257","display_name":"Multiplicity (mathematics)","level":2,"score":0.5277208685874939},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.522363007068634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49126094579696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4173858165740967},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11903917789459229},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08146652579307556},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0729951560497284},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv57701.2024.00443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv57701.2024.00443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1819662813","https://openalex.org/W1834627138","https://openalex.org/W2194775991","https://openalex.org/W2535690855","https://openalex.org/W2768267830","https://openalex.org/W2794284562","https://openalex.org/W2905810301","https://openalex.org/W2911978475","https://openalex.org/W2962787423","https://openalex.org/W2964137095","https://openalex.org/W2982435932","https://openalex.org/W3014590323","https://openalex.org/W3034700241","https://openalex.org/W3035682985","https://openalex.org/W3083393236","https://openalex.org/W3100511085","https://openalex.org/W3118608800","https://openalex.org/W3120460133","https://openalex.org/W3120485916","https://openalex.org/W3135970545","https://openalex.org/W3181414820","https://openalex.org/W3187057914","https://openalex.org/W3202897123","https://openalex.org/W4205228770","https://openalex.org/W4224037372","https://openalex.org/W4283169532","https://openalex.org/W4285162225","https://openalex.org/W4293846201","https://openalex.org/W4297736277","https://openalex.org/W4306955484","https://openalex.org/W4311642023","https://openalex.org/W4312663109","https://openalex.org/W4312809370","https://openalex.org/W4312933868","https://openalex.org/W4366149319","https://openalex.org/W4380320358","https://openalex.org/W4385187849","https://openalex.org/W6637162671","https://openalex.org/W6739868092","https://openalex.org/W6746088618","https://openalex.org/W6746559086","https://openalex.org/W6750964650","https://openalex.org/W6787335730","https://openalex.org/W6787972765","https://openalex.org/W6788494687","https://openalex.org/W6790978476","https://openalex.org/W6792159351","https://openalex.org/W6847118041","https://openalex.org/W6849928207"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2000169967","https://openalex.org/W2112883198"],"abstract_inverted_index":{"Deep":[0],"learning":[1,180],"models":[2,22,181],"have":[3,53],"proven":[4],"to":[5,14,44,67,137,204],"be":[6],"highly":[7],"successful.":[8],"Yet,":[9],"their":[10],"over-parameterization":[11],"gives":[12],"rise":[13],"model":[15,42,94,115,170,188],"multiplicity,":[16],"a":[17,34,69,84,100,110,130,151,206],"phenomenon":[18],"in":[19,41,62,74,140,154,178,212],"which":[20,132],"multiple":[21],"achieve":[23],"similar":[24],"performance":[25],"but":[26],"exhibit":[27],"distinct":[28],"underlying":[29],"behaviours.":[30],"This":[31],"multiplicity":[32,73,89,116,135,139,176,211],"presents":[33],"significant":[35],"challenge":[36],"and":[37,96,157,164,201],"necessitates":[38],"additional":[39,185],"specifications":[40,186],"selection":[43],"prevent":[45],"unexpected":[46],"failures":[47],"during":[48,187],"deployment.":[49],"While":[50],"prior":[51],"studies":[52],"examined":[54],"these":[55],"concerns,":[56],"they":[57],"focus":[58],"on":[59,99,169],"individual":[60],"metrics":[61,121],"isolation,":[63],"making":[64],"it":[65],"difficult":[66],"obtain":[68],"comprehensive":[70,208],"view":[71],"of":[72,88,93,103,147,166,193,197,210],"trustworthy":[75,104,120,213],"machine":[76,214],"learning.":[77,215],"Our":[78],"work":[79],"stands":[80],"out":[81],"by":[82,117],"offering":[83],"one-stop":[85],"empirical":[86],"benchmark":[87,138],"across":[90],"various":[91,141],"dimensions":[92],"design":[95],"its":[97],"impact":[98,163],"diverse":[101],"set":[102],"metrics.In":[105],"this":[106],"work,":[107],"we":[108,133,173,202],"establish":[109],"consistent":[111],"language":[112],"for":[113],"studying":[114],"translating":[118],"several":[119],"into":[122,161],"accuracy":[123],"under":[124],"appropriate":[125],"interventions.":[126],"We":[127,143],"also":[128],"develop":[129],"framework,":[131],"call":[134],"sheets,":[136],"scenarios.":[142],"demonstrate":[144],"the":[145,162,191],"advantages":[146],"our":[148],"setup":[149],"through":[150],"case":[152],"study":[153],"image":[155],"classification":[156],"provide":[158],"actionable":[159],"insights":[160],"trends":[165],"different":[167],"hyperparameters":[168],"multiplicity.":[171],"Finally,":[172],"show":[174],"that":[175],"persists":[177],"deep":[179],"even":[182],"after":[183],"enforcing":[184],"selection,":[189],"highlighting":[190],"severity":[192],"over-parameterization.":[194],"The":[195],"concerns":[196],"under-specification":[198],"thus":[199],"remain,":[200],"seek":[203],"promote":[205],"more":[207],"discussion":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}