{"id":"https://openalex.org/W4372348283","doi":"https://doi.org/10.1109/icassp49357.2023.10095172","title":"Prune Then Distill: Dataset Distillation with Importance Sampling","display_name":"Prune Then Distill: Dataset Distillation with Importance Sampling","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348283","doi":"https://doi.org/10.1109/icassp49357.2023.10095172"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5082376307","display_name":"Anirudh Sundar","orcid":"https://orcid.org/0009-0000-9801-9823"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirudh S Sundar","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026246923","display_name":"Gokce Keskin","orcid":null},"institutions":[{"id":"https://openalex.org/I1336492463","display_name":"American Institute of Mathematics","ror":"https://ror.org/02a0fwv66","country_code":"US","type":"funder","lineage":["https://openalex.org/I1311060795","https://openalex.org/I1336492463"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokce Keskin","raw_affiliation_strings":["Sanas AI,Palo Alto,CA,USA","Sanas AI, Palo Alto, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sanas AI,Palo Alto,CA,USA","institution_ids":["https://openalex.org/I1336492463"]},{"raw_affiliation_string":"Sanas AI, Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057924649","display_name":"Chander Chandak","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chander Chandak","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046605612","display_name":"I\u2010Ming Chen","orcid":"https://orcid.org/0000-0002-4831-3781"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"I-Fan Chen","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029777844","display_name":"Pegah Ghahremani","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pegah Ghahremani","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102095407","display_name":"Shalini Ghosh","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shalini Ghosh","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55481419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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/T12535","display_name":"Machine Learning and Data Classification","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/T12535","display_name":"Machine Learning and Data Classification","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/T12072","display_name":"Machine Learning and Algorithms","score":0.9991000294685364,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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":0.810447096824646},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7833022475242615},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7571426630020142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6243894696235657},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6067788004875183},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5359262824058533},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48865821957588196},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.43987682461738586},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3377637267112732},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.24480405449867249},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10186910629272461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810447096824646},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7833022475242615},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7571426630020142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243894696235657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6067788004875183},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5359262824058533},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48865821957588196},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.43987682461738586},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3377637267112732},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.24480405449867249},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10186910629272461},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095172","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/W1558089843","https://openalex.org/W1821462560","https://openalex.org/W1900116963","https://openalex.org/W2037959456","https://openalex.org/W2117539524","https://openalex.org/W2774918944","https://openalex.org/W2797583228","https://openalex.org/W2951013084","https://openalex.org/W2954732411","https://openalex.org/W3034486793","https://openalex.org/W3048045781","https://openalex.org/W3098758181","https://openalex.org/W3118608800","https://openalex.org/W3130095188","https://openalex.org/W4221145186","https://openalex.org/W4281700249","https://openalex.org/W4283761305","https://openalex.org/W4287077733","https://openalex.org/W4297779241","https://openalex.org/W6633217203","https://openalex.org/W6638523607","https://openalex.org/W6747231328","https://openalex.org/W6750665317","https://openalex.org/W6756054015","https://openalex.org/W6757248479","https://openalex.org/W6765715182","https://openalex.org/W6779630500","https://openalex.org/W6779744012","https://openalex.org/W6781689620","https://openalex.org/W6785612763","https://openalex.org/W6787972765","https://openalex.org/W6790536367","https://openalex.org/W6798413682","https://openalex.org/W6810514673","https://openalex.org/W6839101817","https://openalex.org/W6839990677"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2373300491","https://openalex.org/W2371138613","https://openalex.org/W2395294869","https://openalex.org/W2378744544","https://openalex.org/W2048963458","https://openalex.org/W2594301978","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2379704676"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,12,20,69,103,142],"large":[3,41],"datasets":[4,42,59,90],"for":[5,65],"various":[6],"tasks":[7],"has":[8],"driven":[9],"the":[10,18,66,93],"success":[11],"deep":[13,70],"learning":[14,71],"models":[15],"but":[16],"at":[17],"cost":[19],"increased":[21],"label":[22],"noise,":[23],"duplication,":[24],"collection":[25],"challenges,":[26],"storage":[27],"capabilities,":[28],"and":[29,52,84,105,110,128],"training":[30],"requirements.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,133],"investigate":[36],"whether":[37],"all":[38],"samples":[39,64,83],"in":[40,58,117,139],"contribute":[43],"equally":[44],"to":[45,55,91,113,136],"better":[46],"model":[47],"accuracy.":[48,95],"We":[49,96],"study":[50],"statistical":[51],"mathematical":[53],"techniques":[54],"reduce":[56],"redundancies":[57],"by":[60,146],"directly":[61],"optimizing":[62],"data":[63],"generalization":[67,94,118,140],"accuracy":[68,119,141],"models.":[72],"Existing":[73],"dataset":[74,107,143],"optimization":[75,108],"approaches":[76],"include":[77],"analytic":[78,104],"methods":[79,86],"that":[80,87],"remove":[81],"unimportant":[82],"synthetic":[85,106],"generate":[88],"new":[89],"maximize":[92],"develop":[97],"Prune":[98],"then":[99],"distill,":[100],"a":[101],"combination":[102],"algorithms,":[109],"demonstrate":[111,134],"up":[112,135],"15%":[114],"relative":[115],"improvement":[116,138],"over":[120],"either":[121],"approach":[122],"used":[123],"independently":[124],"on":[125],"standard":[126],"image":[127],"audio":[129],"classification":[130],"tasks.":[131],"Additionally,":[132],"38%":[137],"pruning":[144],"algorithms":[145],"maintaining":[147],"class":[148],"balance":[149],"while":[150],"pruning.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}