{"id":"https://openalex.org/W4415250822","doi":"https://doi.org/10.1109/hpec67600.2025.11196642","title":"Improving Uncertainty Based Dataset Pruning with Density Estimation for Noisy Edge Environments","display_name":"Improving Uncertainty Based Dataset Pruning with Density Estimation for Noisy Edge Environments","publication_year":2025,"publication_date":"2025-09-15","ids":{"openalex":"https://openalex.org/W4415250822","doi":"https://doi.org/10.1109/hpec67600.2025.11196642"},"language":"en","primary_location":{"id":"doi:10.1109/hpec67600.2025.11196642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5119363345","display_name":"Mike Soricelli","orcid":null},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mike Soricelli","raw_affiliation_strings":["University of Massachusetts Dartmouth,Computer & Information Science,Dartmouth,USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Dartmouth,Computer & Information Science,Dartmouth,USA","institution_ids":["https://openalex.org/I100633361"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001829437","display_name":"Yuchou Chang","orcid":"https://orcid.org/0000-0002-9349-4008"},"institutions":[{"id":"https://openalex.org/I100633361","display_name":"University of Massachusetts Dartmouth","ror":"https://ror.org/00fzmm222","country_code":"US","type":"education","lineage":["https://openalex.org/I100633361"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuchou Chang","raw_affiliation_strings":["University of Massachusetts Dartmouth,Computer & Information Science,Dartmouth,USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Dartmouth,Computer & Information Science,Dartmouth,USA","institution_ids":["https://openalex.org/I100633361"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5116485641","display_name":"Christopher J Hixenbaugh","orcid":null},"institutions":[{"id":"https://openalex.org/I1328969757","display_name":"Naval Sea Systems Command","ror":"https://ror.org/03dm1p143","country_code":"US","type":"funder","lineage":["https://openalex.org/I1328969757","https://openalex.org/I1330347796","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J Hixenbaugh","raw_affiliation_strings":["Naval Sea Systems Command,NUWC Division Newport,Newport,USA"],"affiliations":[{"raw_affiliation_string":"Naval Sea Systems Command,NUWC Division Newport,Newport,USA","institution_ids":["https://openalex.org/I1328969757"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5119363345"],"corresponding_institution_ids":["https://openalex.org/I100633361"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1608328,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.4374000132083893,"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":0.4374000132083893,"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/pruning","display_name":"Pruning","score":0.8754000067710876},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.744700014591217},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6133000254631042},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5396000146865845},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4189999997615814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4041000008583069},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3978999853134155},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.37630000710487366}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8754000067710876},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513999938964844},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.744700014591217},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6133000254631042},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6060000061988831},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5396000146865845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5024999976158142},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45680001378059387},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4041000008583069},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.3427000045776367},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.27320000529289246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec67600.2025.11196642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec67600.2025.11196642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE High Performance Extreme Computing Conference (HPEC)","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":3,"referenced_works":["https://openalex.org/W4381888413","https://openalex.org/W4402727870","https://openalex.org/W4402915941"],"related_works":[],"abstract_inverted_index":{"With":[0],"advancements":[1],"in":[2],"machine":[3],"learning":[4],"methods":[5,92],"for":[6,16],"image":[7],"classification,":[8],"models":[9,25,139],"are":[10,93],"getting":[11],"larger":[12],"and":[13,26,43,132,187],"the":[14,37,51,74,86,99,118,147,172,196],"need":[15],"large":[17,129],"datasets":[18,27,71],"is":[19],"increasing.":[20],"Although":[21],"increased":[22,40],"sizes":[23],"of":[24,39,65,76,85,120,143,192],"lead":[28],"to":[29,49,59,72,122,140,149,162,181],"improved":[30,178],"classification":[31,52],"accuracy,":[32],"it":[33],"also":[34,167],"comes":[35],"at":[36],"cost":[38,42],"computational":[41],"energy":[44],"consumption":[45],"on":[46,69],"edge":[47],"devices":[48],"train":[50],"model.":[53],"Data-centric":[54],"approaches":[55,67],"have":[56],"been":[57],"proposed":[58],"address":[60],"this":[61,106],"problem.":[62],"An":[63],"area":[64],"data-centric":[66],"focuses":[68],"pruning":[70,91,142,154],"minimize":[73],"size":[75],"training":[77,121],"data":[78,114,125,145],"while":[79,166],"maintaining":[80],"model":[81],"performance.":[82],"Current":[83],"State":[84],"Art":[87],"prediction":[88],"uncertainty-based":[89,164],"dataset":[90,101,131,148,153],"effective,":[94],"but":[95],"they":[96],"struggle":[97],"when":[98],"target":[100,173],"contains":[102],"noisy":[103,169],"images.":[104],"In":[105],"work,":[107],"we":[108],"adapt":[109],"prior":[110],"works":[111],"that":[112],"use":[113],"uncertainty":[115],"calculations":[116],"over":[117],"course":[119],"prune":[123],"easy-to-learn":[124],"points":[126],"from":[127,146,171],"a":[128,151],"scale":[130],"add":[133],"density":[134,157],"estimation":[135,158],"utilizing":[136],"normalizing":[137],"flow":[138],"encourage":[141],"outlier":[144],"create":[150],"novel":[152],"method.":[155],"Using":[156],"allows":[159],"our":[160],"method":[161],"perform":[163],"pruning,":[165],"removing":[168],"images":[170],"dataset.":[174],"Experimental":[175],"results":[176],"show":[177],"accuracy":[179],"up":[180],"1.11%":[182],"with":[183,189,195],"moderate":[184],"noise":[185,193],"injection":[186,194],"4.00%":[188],"high":[190],"levels":[191],"weighted":[197],"score-based":[198],"approach.":[199]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-16T00:00:00"}