{"id":"https://openalex.org/W4388102963","doi":"https://doi.org/10.1109/soli57430.2022.10294527","title":"Leveraging Explainable Artificial Intelligence for Understanding the Effect of Model Capacity on Training Dataset Size","display_name":"Leveraging Explainable Artificial Intelligence for Understanding the Effect of Model Capacity on Training Dataset Size","publication_year":2022,"publication_date":"2022-12-02","ids":{"openalex":"https://openalex.org/W4388102963","doi":"https://doi.org/10.1109/soli57430.2022.10294527"},"language":"en","primary_location":{"id":"doi:10.1109/soli57430.2022.10294527","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/soli57430.2022.10294527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","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/A5040028854","display_name":"Tushar Prakash","orcid":"https://orcid.org/0009-0003-4691-3526"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tushar Prakash","raw_affiliation_strings":["Delhi Technological University,Electronics and Communication Department,Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Electronics and Communication Department,Delhi,India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020519974","display_name":"Tashvik Dhamija","orcid":null},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Tashvik Dhamija","raw_affiliation_strings":["Delhi Technological University,Electronics and Communication Department,Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Electronics and Communication Department,Delhi,India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624406","display_name":"Rohit Kumar","orcid":"https://orcid.org/0000-0001-7067-1852"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rohit Kumar","raw_affiliation_strings":["Delhi Technological University,Electronics and Communication Department,Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Electronics and Communication Department,Delhi,India","institution_ids":["https://openalex.org/I863896202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025671561","display_name":"Jeebananda Panda","orcid":"https://orcid.org/0000-0002-5325-320X"},"institutions":[{"id":"https://openalex.org/I863896202","display_name":"Delhi Technological University","ror":"https://ror.org/01ztcvt22","country_code":"IN","type":"education","lineage":["https://openalex.org/I863896202"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jeebananda Panda","raw_affiliation_strings":["Delhi Technological University,Electronics and Communication Department,Delhi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delhi Technological University,Electronics and Communication Department,Delhi,India","institution_ids":["https://openalex.org/I863896202"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I863896202"],"apc_list":null,"apc_paid":null,"fwci":0.1388,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59022674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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":0.9925000071525574,"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":0.9925000071525574,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9828000068664551,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9686999917030334,"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":0.7644228935241699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6448377370834351},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6203651428222656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5176916122436523},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46665382385253906},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4497969150543213},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.07851213216781616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7644228935241699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6448377370834351},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6203651428222656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5176916122436523},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46665382385253906},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4497969150543213},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.07851213216781616},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/soli57430.2022.10294527","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/soli57430.2022.10294527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI)","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":36,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2032054866","https://openalex.org/W2044097773","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2344480160","https://openalex.org/W2431355146","https://openalex.org/W2475566629","https://openalex.org/W2516809705","https://openalex.org/W2549139847","https://openalex.org/W2913813112","https://openalex.org/W2922019699","https://openalex.org/W2962858109","https://openalex.org/W2962862931","https://openalex.org/W3120430728","https://openalex.org/W3127001844","https://openalex.org/W3138516171","https://openalex.org/W3149847987","https://openalex.org/W3200157976","https://openalex.org/W3200842935","https://openalex.org/W3216978859","https://openalex.org/W4210512387","https://openalex.org/W4220851149","https://openalex.org/W4226275002","https://openalex.org/W4226325015","https://openalex.org/W4288062034","https://openalex.org/W4294310817","https://openalex.org/W4294975187","https://openalex.org/W4321197496","https://openalex.org/W4389961269","https://openalex.org/W4391582461","https://openalex.org/W6603391536","https://openalex.org/W6637373629","https://openalex.org/W6726258750","https://openalex.org/W6737947904","https://openalex.org/W6792155083"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Automated":[0],"Image":[1,121],"classification":[2,24],"has":[3],"seen":[4],"substantial":[5],"growth":[6],"in":[7,78,96,223,257],"recent":[8],"times.":[9],"However,":[10,75],"several":[11,103],"applications":[12,55,67],"suffer":[13],"from":[14],"the":[15,23,46,76,97,153,170,225,247,253,258],"limited":[16,33,47],"availability":[17,48],"of":[18,25,37,49,53,99,192,239,249,255],"training":[19,50,141,164,176,206,259],"data,":[20,51],"such":[21,119],"as":[22,120],"medical":[26,90,100,127,162,175],"images,":[27,101],"where":[28,102],"data":[29],"collection":[30],"is":[31],"mostly":[32],"by":[34,156],"privacy":[35],"concerns":[36],"human":[38],"subjects.":[39],"As":[40],"a":[41,189],"result,":[42],"to":[43,131,137,151,187,212,232,245,273,304],"compensate":[44],"for":[45,64,112,160,173],"most":[52,108],"these":[54],"employ":[56],"custom-made":[57],"lightweight":[58],"architectures.":[59],"While":[60],"state-of-the-art":[61,157],"deep":[62,110,158],"models":[63,159,201,265,281,289],"computer":[65,113],"vision":[66,114],"usually":[68],"exploit":[69,147,181],"architectures":[70],"with":[71,169,204],"huge":[72,132],"model":[73,79,133,227,250],"capacity.":[74],"increase":[77],"complexity":[80,251],"and":[81,166,196,298],"size":[82],"necessarily":[83],"doesn't":[84],"guarantee":[85],"better":[86,275],"performance":[87],"on":[88,116,126,139,221,229,236,252,276,284,292],"small":[89,277],"datasets.":[91,142,177,286],"We":[92],"study":[93],"this":[94,144],"phenomenon":[95],"context":[98],"existing":[104],"studies":[105],"report":[106],"that":[107,263,270,301],"sophisticated":[109],"networks":[111],"trained":[115,203,283,291],"large":[117],"datasets":[118,165,238,294],"Net":[122],"do":[123],"not":[124],"generalize":[125],"image":[128,163,210],"applications,":[129],"due":[130],"capacity,":[134],"subsequently":[135],"leading":[136],"overfitting":[138],"smaller":[140,161,285,306],"In":[143,178],"research,":[145],"we":[146,180,216],"explainable":[148],"artificial":[149],"intelligence":[150],"analyze":[152],"features":[154,171,186,220,269,300],"learned":[155,172],"contrast":[167],"them":[168,272,303],"larger":[174,280,293],"particular,":[179],"Shapley":[182],"Additive":[183],"explanations":[184],"(SHAP)":[185],"perform":[188,213,274],"qualitative":[190],"comparison":[191],"feature":[193],"relevance":[194],"maps":[195],"understand":[197,208,246],"how":[198],"different":[199,205,233,240],"standard":[200],"when":[202,282,290],"sizes":[207,241],"discriminative":[209],"patterns":[211],"classification.":[214],"Furthermore,":[215],"also":[217],"compare":[218],"SHAP":[219,268],"scenarios":[222],"which":[224],"same":[226],"focuses":[228],"images":[230],"belonging":[231],"classes.":[234],"Experiments":[235],"two":[237],"have":[242],"been":[243],"presented":[244],"dependence":[248],"number":[254],"samples":[256],"dataset.":[260],"Results":[261],"demonstrate":[262],"simpler":[264],"learn":[266,295],"generalizable":[267],"allow":[271,302],"datasets,":[278],"unlike":[279],"Likewise,":[287],"bigger":[288],"more":[296],"distinctive":[297],"diverse":[299],"outperform":[305],"models.":[307]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}