{"id":"https://openalex.org/W4403702901","doi":"https://doi.org/10.1109/icmla66185.2025.00138","title":"Kolmogorov-Arnold Networks in Low-Data Regimes: A Comparative Study with Multilayer Perceptrons","display_name":"Kolmogorov-Arnold Networks in Low-Data Regimes: A Comparative Study with Multilayer Perceptrons","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4403702901","doi":"https://doi.org/10.1109/icmla66185.2025.00138"},"language":"en","primary_location":{"id":"doi:10.1109/icmla66185.2025.00138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2409.10463","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043966041","display_name":"Farhad Pourkamali\u2010Anaraki","orcid":"https://orcid.org/0000-0003-4078-1676"},"institutions":[{"id":"https://openalex.org/I1343558604","display_name":"Statistical and Applied Mathematical Sciences Institute","ror":"https://ror.org/01shctp43","country_code":"US","type":"facility","lineage":["https://openalex.org/I1311060795","https://openalex.org/I1343558604"]},{"id":"https://openalex.org/I4210157790","display_name":"Statistical Research (United States)","ror":"https://ror.org/058eg8775","country_code":"US","type":"company","lineage":["https://openalex.org/I4210157790"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Farhad Pourkamali-Anaraki","raw_affiliation_strings":["University of Colorado,Department of Mathematical and Statistical Sciences,Denver,CO,USA"],"affiliations":[{"raw_affiliation_string":"University of Colorado,Department of Mathematical and Statistical Sciences,Denver,CO,USA","institution_ids":["https://openalex.org/I1343558604","https://openalex.org/I4210157790"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5043966041"],"corresponding_institution_ids":["https://openalex.org/I1343558604","https://openalex.org/I4210157790"],"apc_list":null,"apc_paid":null,"fwci":4.663,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93350118,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"923","last_page":"928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9380000233650208,"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/T10320","display_name":"Neural Networks and Applications","score":0.9380000233650208,"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/perceptron","display_name":"Perceptron","score":0.739946722984314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4398321807384491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4089335501194},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2774351239204407}],"concepts":[{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.739946722984314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4398321807384491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4089335501194},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2774351239204407}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmla66185.2025.00138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2409.10463","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.10463","pdf_url":"https://arxiv.org/pdf/2409.10463","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2409.10463","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.10463","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.10463","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.10463","pdf_url":"https://arxiv.org/pdf/2409.10463","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403702901.pdf","grobid_xml":"https://content.openalex.org/works/W4403702901.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Multilayer":[0],"Perceptrons":[1],"(MLPs)":[2],"have":[3,23],"long":[4],"been":[5],"a":[6,26,39,68,83,105,147,166,174,185],"cornerstone":[7],"in":[8,61,150,165],"deep":[9],"learning,":[10],"known":[11],"for":[12,93,101],"their":[13,59],"capacity":[14],"to":[15,159],"model":[16,128],"complex":[17],"relationships.":[18],"Recently,":[19],"Kolmogorov-Arnold":[20],"Networks":[21],"(KANs)":[22],"emerged":[24],"as":[25],"compelling":[27],"alternative,":[28],"utilizing":[29],"highly":[30],"flexible":[31],"learnable":[32,54],"activation":[33,99,139,208],"functions":[34,100,140],"directly":[35],"on":[36,85,114],"network":[37],"edges,":[38],"departure":[40],"from":[41,76,119],"the":[42,51,125,154,200],"neuron-centric":[43],"approach":[44],"of":[45,53,72,177,188,206],"MLPs.":[46],"However,":[47],"KANs":[48,75],"significantly":[49,179],"increase":[50,149],"number":[52],"parameters,":[55,151],"raising":[56],"concerns":[57],"about":[58],"effectiveness":[60],"data-scarce":[62],"environments.":[63],"Hence,":[64],"this":[65],"paper":[66],"presents":[67],"comprehensive":[69],"comparative":[70],"study":[71],"MLPs":[73,95,136,172],"and":[74,79,121,130,203],"both":[77],"algorithmic":[78],"experimental":[80],"perspectives,":[81],"with":[82,96,109,137,145],"focus":[84],"low-data":[86],"regimes.":[87],"We":[88],"introduce":[89],"an":[90],"effective":[91],"technique":[92],"designing":[94],"unique,":[97],"parameterized":[98],"each":[102],"neuron,":[103],"enabling":[104],"more":[106],"balanced":[107],"comparison":[108],"KANs.":[110],"Using":[111],"empirical":[112],"evaluations":[113],"two":[115],"real-world":[116],"data":[117],"sets":[118],"medicine":[120],"engineering,":[122],"we":[123,192],"explore":[124],"trade-offs":[126],"between":[127],"complexity":[129],"accuracy.":[131],"Our":[132],"findings":[133],"show":[134],"that":[135],"individualized":[138],"achieve":[141,173],"higher":[142],"predictive":[143],"accuracy":[144,176,187],"only":[146,183],"modest":[148],"especially":[152],"when":[153],"sample":[155],"size":[156,205],"is":[157],"limited":[158],"around":[160],"one":[161],"hundred.":[162],"For":[163],"example,":[164],"classification":[167],"problem":[168],"within":[169],"additive":[170],"manufacturing,":[171],"median":[175,186],"0.91,":[178],"outperforming":[180],"KANs,":[181],"which":[182],"reach":[184],"0.53.":[189],"In":[190],"addition,":[191],"analyze":[193],"key":[194],"factors":[195],"affecting":[196],"KAN":[197],"performance,":[198],"including":[199],"polynomial":[201],"order":[202],"grid":[204],"spline-based":[207],"functions.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2024-10-24T00:00:00"}