{"id":"https://openalex.org/W4410583036","doi":"https://doi.org/10.23919/date64628.2025.10992874","title":"Enabling Memory-Efficient On-Device Learning via Dataset Condensation","display_name":"Enabling Memory-Efficient On-Device Learning via Dataset Condensation","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410583036","doi":"https://doi.org/10.23919/date64628.2025.10992874"},"language":"en","primary_location":{"id":"doi:10.23919/date64628.2025.10992874","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","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/A5104315310","display_name":"Gelei Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gelei Xu","raw_affiliation_strings":["University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067692414","display_name":"Ningzhi Tang","orcid":"https://orcid.org/0000-0002-8555-2351"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ningzhi Tang","raw_affiliation_strings":["University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081669284","display_name":"Jun Xia","orcid":"https://orcid.org/0000-0003-0245-8499"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Xia","raw_affiliation_strings":["University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106463942","display_name":"Ruiyang Qin","orcid":"https://orcid.org/0000-0003-0827-2257"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruiyang Qin","raw_affiliation_strings":["University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100840965","display_name":"Wei Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Jin","raw_affiliation_strings":["Emory University"],"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000141831","display_name":"Yiyu Shi","orcid":"https://orcid.org/0000-0002-6788-9823"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiyu Shi","raw_affiliation_strings":["University of Notre Dame"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5104315310"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05663125,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8960999846458435,"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":0.8960999846458435,"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/computer-science","display_name":"Computer science","score":0.6821764707565308},{"id":"https://openalex.org/keywords/condensation","display_name":"Condensation","score":0.5572552680969238},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4647613763809204},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3742489814758301},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.2101525366306305},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18569514155387878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6821764707565308},{"id":"https://openalex.org/C200093464","wikidata":"https://www.wikidata.org/wiki/Q166583","display_name":"Condensation","level":2,"score":0.5572552680969238},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4647613763809204},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3742489814758301},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.2101525366306305},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18569514155387878},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date64628.2025.10992874","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date64628.2025.10992874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W2079582948","https://openalex.org/W2119885577","https://openalex.org/W2743151379","https://openalex.org/W2798836702","https://openalex.org/W2964189064","https://openalex.org/W2968596670","https://openalex.org/W2986358680","https://openalex.org/W3035160371","https://openalex.org/W3082248862","https://openalex.org/W3108655343","https://openalex.org/W3113055207","https://openalex.org/W3213582899","https://openalex.org/W4283076909","https://openalex.org/W4308480033","https://openalex.org/W4312292108","https://openalex.org/W4312412605","https://openalex.org/W4319300193","https://openalex.org/W4385555283","https://openalex.org/W4386113256","https://openalex.org/W4390357221","https://openalex.org/W4392173735","https://openalex.org/W4393168987","https://openalex.org/W4401478512","https://openalex.org/W4404134039","https://openalex.org/W4409282487","https://openalex.org/W4409306189","https://openalex.org/W6737377802","https://openalex.org/W6747231328","https://openalex.org/W6749866413","https://openalex.org/W6752515464","https://openalex.org/W6756054015","https://openalex.org/W6763462227","https://openalex.org/W6764645560","https://openalex.org/W6768926992","https://openalex.org/W6776188292","https://openalex.org/W6776700526","https://openalex.org/W6779101013","https://openalex.org/W6779630500","https://openalex.org/W6790536367","https://openalex.org/W6796435857","https://openalex.org/W6811426508","https://openalex.org/W6839101817","https://openalex.org/W6869453251"],"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":{"Upon":[0],"deployment":[1],"to":[2,12,18,45,52,57,67,82,114,147,168,210],"edge":[3,65],"devices,":[4],"it":[5,29],"is":[6,26,30,56,89,143],"often":[7],"desirable":[8],"for":[9,75,126,138],"a":[10,59,99,122,133,164,191,203],"model":[11],"further":[13,162],"learn":[14],"from":[15,23],"streaming":[16],"data":[17,25,61,74,88,108],"improve":[19,169],"accuracy.":[20],"However,":[21,77],"learning":[22,128,140],"such":[24],"challenging":[27],"because":[28],"typically":[31],"unlabeled,":[32],"non-independent":[33],"and":[34,38,69],"identically":[35],"distributed":[36],"(non-i.i.d),":[37],"only":[39],"seen":[40],"once,":[41],"which":[42,142],"can":[43],"lead":[44],"potential":[46],"catastrophic":[47],"forgetting.":[48],"A":[49],"common":[50],"strategy":[51],"mitigate":[53],"this":[54,103],"issue":[55,104],"maintain":[58],"small":[60],"buffer":[62,186,192],"on":[63,215],"the":[64,71,78,152,158,170,211,216],"device":[66],"select":[68],"retain":[70],"most":[72,87],"representative":[73],"rehearsal.":[76],"selection":[79],"process":[80],"leads":[81],"significant":[83],"information":[84],"loss":[85],"since":[86],"either":[90],"never":[91],"stored":[92],"or":[93],"quickly":[94],"discarded.":[95],"This":[96],"paper":[97],"proposes":[98],"framework":[100],"that":[101],"addresses":[102],"by":[105],"condensing":[106],"incoming":[107,118],"into":[109],"informative":[110],"synthetic":[111],"samples.":[112],"Specifically,":[113],"effectively":[115],"handle":[116],"unlabeled":[117],"data,":[119],"we":[120,161],"propose":[121],"pseudo-labeling":[123],"technique":[124,136],"designed":[125],"on-device":[127,139],"environments.":[129],"We":[130],"also":[131],"develop":[132],"dataset":[134],"condensation":[135,159],"tailored":[137],"scenarios,":[141],"significantly":[144],"faster":[145],"compared":[146,209],"previous":[148],"methods.":[149],"To":[150],"counteract":[151],"effects":[153],"of":[154,172,194],"noisy":[155],"labels":[156],"during":[157],"process,":[160],"utilize":[163],"feature":[165],"discrimination":[166],"objective":[167],"purity":[171],"class":[173],"data.":[174],"Experimental":[175],"results":[176],"indicate":[177],"substantial":[178],"improvements":[179],"over":[180],"existing":[181,213],"methods,":[182],"especially":[183],"under":[184],"strict":[185],"limitations.":[187],"For":[188],"instance,":[189],"with":[190],"capacity":[193],"just":[195],"one":[196],"sample":[197],"per":[198],"class,":[199],"our":[200],"method":[201],"achieves":[202],"56.7%":[204],"relative":[205],"increase":[206],"in":[207],"accuracy":[208],"best":[212],"baseline":[214],"CORe50":[217],"dataset.":[218]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}