{"id":"https://openalex.org/W4386764188","doi":"https://doi.org/10.1109/dac56929.2023.10247716","title":"Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off","display_name":"Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off","publication_year":2023,"publication_date":"2023-07-09","ids":{"openalex":"https://openalex.org/W4386764188","doi":"https://doi.org/10.1109/dac56929.2023.10247716"},"language":"en","primary_location":{"id":"doi:10.1109/dac56929.2023.10247716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","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/A5073345631","display_name":"Shaoyi Huang","orcid":"https://orcid.org/0000-0001-6093-9798"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shaoyi Huang","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087003069","display_name":"Bowen Lei","orcid":"https://orcid.org/0000-0003-2882-9753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Lei","raw_affiliation_strings":["Texas A&M University"],"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068433690","display_name":"Dongkuan Xu","orcid":"https://orcid.org/0000-0002-1456-9658"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dongkuan Xu","raw_affiliation_strings":["North Carolina State University"],"affiliations":[{"raw_affiliation_string":"North Carolina State University","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045835605","display_name":"Hongwu Peng","orcid":"https://orcid.org/0000-0003-2025-2195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongwu Peng","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100591116","display_name":"Yue Sun","orcid":"https://orcid.org/0009-0008-5528-2566"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Sun","raw_affiliation_strings":["Lehigh University"],"affiliations":[{"raw_affiliation_string":"Lehigh University","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059911353","display_name":"Mimi Xie","orcid":"https://orcid.org/0000-0003-1973-2909"},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mimi Xie","raw_affiliation_strings":["University of Texas at San Antonio"],"affiliations":[{"raw_affiliation_string":"University of Texas at San Antonio","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut"],"affiliations":[{"raw_affiliation_string":"University of Connecticut","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5073345631"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6141,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69740348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9940999746322632,"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/T12676","display_name":"Machine Learning and ELM","score":0.989300012588501,"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":0.7465107440948486},{"id":"https://openalex.org/keywords/residual-neural-network","display_name":"Residual neural network","score":0.5686569809913635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.536392092704773},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5174325108528137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5030366778373718},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4756576418876648},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.4498788118362427},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43765944242477417},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.43740737438201904},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.436229407787323},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3452182412147522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7465107440948486},{"id":"https://openalex.org/C2944601119","wikidata":"https://www.wikidata.org/wiki/Q43744058","display_name":"Residual neural network","level":3,"score":0.5686569809913635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536392092704773},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5174325108528137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5030366778373718},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4756576418876648},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4498788118362427},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43765944242477417},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.43740737438201904},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.436229407787323},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3452182412147522},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac56929.2023.10247716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1044919269","https://openalex.org/W1968075052","https://openalex.org/W2294347342","https://openalex.org/W2589646680","https://openalex.org/W2614119628","https://openalex.org/W2768501777","https://openalex.org/W2798170643","https://openalex.org/W2808133870","https://openalex.org/W2894740066","https://openalex.org/W2949413532","https://openalex.org/W2956434358","https://openalex.org/W2990377266","https://openalex.org/W2990844796","https://openalex.org/W2995816250","https://openalex.org/W3005273253","https://openalex.org/W3005842225","https://openalex.org/W3095203791","https://openalex.org/W3104688113","https://openalex.org/W3128194313","https://openalex.org/W3162542754","https://openalex.org/W3171463583","https://openalex.org/W3176468986","https://openalex.org/W3205816523","https://openalex.org/W3206837665","https://openalex.org/W3209017628","https://openalex.org/W3213238321","https://openalex.org/W4226075153","https://openalex.org/W4283219972","https://openalex.org/W4287117188","https://openalex.org/W4287204036","https://openalex.org/W4292779060","https://openalex.org/W4312400543","https://openalex.org/W6734169003","https://openalex.org/W6737650911","https://openalex.org/W6745668070","https://openalex.org/W6750209611","https://openalex.org/W6755166560","https://openalex.org/W6757914502","https://openalex.org/W6765532259","https://openalex.org/W6770699648","https://openalex.org/W6772027524","https://openalex.org/W6772029579","https://openalex.org/W6773667195","https://openalex.org/W6779460946","https://openalex.org/W6790057022","https://openalex.org/W6790215600","https://openalex.org/W6794426595","https://openalex.org/W6797787563","https://openalex.org/W6798034730","https://openalex.org/W6802873456","https://openalex.org/W6803815625","https://openalex.org/W6839802452"],"related_works":["https://openalex.org/W2091883426","https://openalex.org/W2174948646","https://openalex.org/W3173235360","https://openalex.org/W2024017047","https://openalex.org/W4318256793","https://openalex.org/W2594370889","https://openalex.org/W2390720471","https://openalex.org/W2051410394","https://openalex.org/W1600789676","https://openalex.org/W2134327945"],"abstract_inverted_index":{"Over-parameterization":[0],"of":[1,19,39,102,151],"deep":[2,152],"neural":[3],"networks":[4],"(DNNs)":[5],"has":[6,28,167,181],"shown":[7],"high":[8],"prediction":[9],"accuracy":[10,170,185],"for":[11,117],"many":[12],"applications.":[13],"Although":[14],"effective,":[15],"the":[16,48,53,114,118,142,178],"large":[17],"number":[18,38],"parameters":[20],"hinders":[21],"its":[22,123],"popularity":[23],"on":[24,147],"resource-limited":[25],"devices":[26],"and":[27,73,89,98,112,121],"an":[29,109],"outsize":[30],"environmental":[31],"impact.":[32],"Sparse":[33,95],"training":[34,49,59,145,191],"(using":[35],"a":[36,148],"fixed":[37],"nonzero":[40],"weights":[41,87],"in":[42,70],"each":[43],"iteration)":[44],"could":[45],"significantly":[46],"mitigate":[47],"costs":[50],"by":[51,137],"reducing":[52],"model":[54],"size.":[55],"However,":[56],"existing":[57],"sparse":[58,82,130,144,190],"methods":[60,146],"mainly":[61],"use":[62],"either":[63],"random-based":[64],"or":[65],"greedy-based":[66],"drop-and-grow":[67],"strategies,":[68],"resulting":[69],"local":[71],"minimal":[72],"low":[74],"accuracy.":[75],"In":[76],"this":[77],"work,":[78],"to":[79,92,133,183,188],"assist":[80],"explainable":[81],"training,":[83],"we":[84],"propose":[85],"important":[86],"Exploitation":[88],"coverage":[90],"Exploration":[91],"characterize":[93],"Dynamic":[94],"Training":[96],"(DST-EE),":[97],"provide":[99,113],"quantitative":[100],"analysis":[101],"these":[103],"two":[104],"metrics.":[105],"We":[106],"further":[107],"design":[108],"acquisition":[110],"function":[111],"theoretical":[115],"guarantees":[116],"proposed":[119,139,179],"method":[120,140,166,180],"clarify":[122],"convergence":[124],"property.":[125],"Experimental":[126],"results":[127],"show":[128],"that":[129],"models":[131],"(up":[132],"98%":[134],"sparsity)":[135],"obtained":[136],"our":[138,165],"outperform":[141],"SOTA":[143,189],"wide":[149],"variety":[150],"learning":[153],"tasks.":[154],"On":[155,174],"VGG-19":[156],"/":[157,160,163,176],"CIFAR-100,":[158,164],"ResNet-50":[159,162,175],"CIFAR-10,":[161],"even":[168],"higher":[169],"than":[171],"dense":[172],"models.":[173],"ImageNet,":[177],"up":[182],"8.2%":[184],"improvement":[186],"compared":[187],"methods.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}