{"id":"https://openalex.org/W2983647115","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533769","title":"Soft-Label Dataset Distillation and Text Dataset Distillation","display_name":"Soft-Label Dataset Distillation and Text Dataset Distillation","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W2983647115","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533769","mag":"2983647115"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.02551","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053200092","display_name":"Ilia Sucholutsky","orcid":"https://orcid.org/0000-0003-4121-7479"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ilia Sucholutsky","raw_affiliation_strings":["Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada","University of WAterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of WAterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042203967","display_name":"Matthias Schonlau","orcid":"https://orcid.org/0009-0007-3651-9268"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthias Schonlau","raw_affiliation_strings":["Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada","University of WAterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of WAterloo","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":3.3707,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93810294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.996999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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/distillation","display_name":"Distillation","score":0.8275986909866333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7608644962310791},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6119107007980347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5740928053855896},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5664883852005005},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5541048049926758},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5133125185966492},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5013744831085205},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.48613402247428894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4302125573158264},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42127513885498047},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2494506537914276},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.07415321469306946},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0630246102809906}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.8275986909866333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608644962310791},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6119107007980347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5740928053855896},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5664883852005005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5541048049926758},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5133125185966492},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5013744831085205},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.48613402247428894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4302125573158264},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42127513885498047},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2494506537914276},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.07415321469306946},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0630246102809906},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.02551","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.02551","pdf_url":"https://arxiv.org/pdf/1910.02551","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2983647115","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.02551","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.02551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.02551","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.02551","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.02551","pdf_url":"https://arxiv.org/pdf/1910.02551","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.9200000166893005,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1533861849","https://openalex.org/W1583071929","https://openalex.org/W1821462560","https://openalex.org/W2001619934","https://openalex.org/W2064675550","https://openalex.org/W2068514419","https://openalex.org/W2086511124","https://openalex.org/W2099471712","https://openalex.org/W2112796928","https://openalex.org/W2113459411","https://openalex.org/W2127452375","https://openalex.org/W2131774270","https://openalex.org/W2151537585","https://openalex.org/W2155319834","https://openalex.org/W2173520492","https://openalex.org/W2194321275","https://openalex.org/W2250539671","https://openalex.org/W2251939518","https://openalex.org/W2294370754","https://openalex.org/W2295030615","https://openalex.org/W2426031434","https://openalex.org/W2463507112","https://openalex.org/W2570764145","https://openalex.org/W2612467436","https://openalex.org/W2785533664","https://openalex.org/W2787560479","https://openalex.org/W2948223045","https://openalex.org/W2949071206","https://openalex.org/W2949999304","https://openalex.org/W2962739339","https://openalex.org/W2962902328","https://openalex.org/W2963341956","https://openalex.org/W2963470893","https://openalex.org/W2963736842","https://openalex.org/W2963767194","https://openalex.org/W2963809228","https://openalex.org/W2963902936","https://openalex.org/W2964268978","https://openalex.org/W3021654819","https://openalex.org/W3090552759","https://openalex.org/W3118608800","https://openalex.org/W3122408561","https://openalex.org/W6631943919","https://openalex.org/W6638523607","https://openalex.org/W6672077861","https://openalex.org/W6676984168","https://openalex.org/W6683152347","https://openalex.org/W6691459498","https://openalex.org/W6715102896","https://openalex.org/W6735236233","https://openalex.org/W6737232052","https://openalex.org/W6743661861","https://openalex.org/W6747231328","https://openalex.org/W6752089545","https://openalex.org/W6753264383","https://openalex.org/W6756054015","https://openalex.org/W6771536673","https://openalex.org/W6778883912","https://openalex.org/W6779409229","https://openalex.org/W6780534440","https://openalex.org/W6782005658","https://openalex.org/W6782937392","https://openalex.org/W6783201573","https://openalex.org/W6783568346"],"related_works":["https://openalex.org/W2963902936","https://openalex.org/W3198953397","https://openalex.org/W2112796928","https://openalex.org/W1821462560","https://openalex.org/W3118608800","https://openalex.org/W3035559424","https://openalex.org/W2612467436","https://openalex.org/W3086607822","https://openalex.org/W2194775991","https://openalex.org/W3164560392","https://openalex.org/W3119342105","https://openalex.org/W2963341924","https://openalex.org/W2750384547","https://openalex.org/W2601450892","https://openalex.org/W2570764145","https://openalex.org/W2155319834","https://openalex.org/W3000361573","https://openalex.org/W3134074091","https://openalex.org/W3027324862","https://openalex.org/W3139144418"],"abstract_inverted_index":{"Dataset":[0],"distillation":[1,71,172,182],"is":[2,62],"a":[3,11,64,94,139],"method":[4],"for":[5,107,133],"reducing":[6,28,32],"dataset":[7,70,171],"sizes":[8],"by":[9,52,105],"learning":[10,45],"small":[12],"number":[13],"of":[14,99,121],"representative":[15],"synthetic":[16,60,92],"samples.":[17],"This":[18],"has":[19],"several":[20,108],"benefits":[21,37],"such":[22],"as":[23,128],"speeding":[24],"up":[25],"model":[26,141],"training,":[27],"energy":[29],"consumption,":[30],"and":[31,68,86,156],"required":[33],"storage":[34],"space.":[35],"These":[36],"are":[38,50,126],"especially":[39],"crucial":[40],"in":[41,150],"settings":[42],"like":[43],"federated":[44],"where":[46],"initial":[47],"overhead":[48],"costs":[49],"justified":[51],"the":[53,170,198],"speedup":[54],"they":[55],"enable.":[56],"Currently,":[57],"1)":[58],"each":[59,91,129],"sample":[61,93,130],"assigned":[63],"single":[65],"\u2018hard\u2019":[66],"label,":[67],"2)":[69],"can":[72,210],"only":[73],"be":[74,211],"used":[75],"with":[76,142],"image":[77,109],"data.":[78,177],"We":[79,167,178],"propose":[80],"to":[81,119,174],"simultaneously":[82],"distill":[83,175],"both":[84],"images":[85,145],"their":[87,194],"labels,":[88],"thus":[89],"assigning":[90],"\u2018soft\u2019":[95,113],"label":[96],"(a":[97],"distribution":[98],"labels).":[100],"Our":[101,208],"algorithm":[102,173],"increases":[103],"accuracy":[104,153,159,196],"2-4%":[106],"classification":[110],"tasks.":[111],"Using":[112],"labels":[114],"also":[115,168],"enables":[116],"distilled":[117,144,165,206],"datasets":[118],"consist":[120],"fewer":[122],"samples":[123],"than":[124],"there":[125],"classes":[127],"encodes":[131],"information":[132],"multiple":[134,187],"classes.":[135],"For":[136,189],"example,":[137,190],"training":[138],"LeNet":[140],"10":[143],"(one":[146],"per":[147],"class)":[148],"results":[149],"over":[151],"96%":[152],"on":[154,162,197],"MNIST,":[155],"almost":[157,193],"92%":[158],"when":[160],"trained":[161],"just":[163,204],"5":[164],"images.":[166],"extend":[169],"text":[176,181],"demonstrate":[179],"that":[180],"outperforms":[183],"other":[184],"methods":[185],"across":[186],"datasets.":[188],"models":[191],"attain":[192],"original":[195],"IMDB":[199],"sentiment":[200],"analysis":[201],"task":[202],"using":[203],"20":[205],"sentences.":[207],"code":[209],"found":[212],"at":[213],"https://github.com/ilia10000/dataset-distillation.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":7}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}