{"id":"https://openalex.org/W4406859087","doi":"https://doi.org/10.1109/ipccc59868.2024.10850369","title":"DP-Prune: Global Optimal Strategy for Retraining-Free Pruning of Transformer Models","display_name":"DP-Prune: Global Optimal Strategy for Retraining-Free Pruning of Transformer Models","publication_year":2024,"publication_date":"2024-11-22","ids":{"openalex":"https://openalex.org/W4406859087","doi":"https://doi.org/10.1109/ipccc59868.2024.10850369"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc59868.2024.10850369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc59868.2024.10850369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Performance, Computing, and Communications Conference (IPCCC)","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/A5065454900","display_name":"Guangzhen Yao","orcid":"https://orcid.org/0009-0002-1323-6998"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhen Yao","raw_affiliation_strings":["Northeast Normal University,Changchun,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,Changchun,China","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114137495","display_name":"Long Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zhang","raw_affiliation_strings":["Northeast Normal University,Changchun,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,Changchun,China","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100598322","display_name":"Sandong Zhu","orcid":"https://orcid.org/0009-0005-2104-9887"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sandong Zhu","raw_affiliation_strings":["Northeast Normal University,Changchun,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,Changchun,China","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101535006","display_name":"Miao Qi","orcid":"https://orcid.org/0000-0002-5932-4435"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Qi","raw_affiliation_strings":["Northeast Normal University,Changchun,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northeast Normal University,Changchun,China","institution_ids":["https://openalex.org/I184983240"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184983240"],"apc_list":null,"apc_paid":null,"fwci":6.7961,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97427521,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"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/T11222","display_name":"Magnetic Properties and Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11222","display_name":"Magnetic Properties and Applications","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11343","display_name":"Power Transformer Diagnostics and Insulation","score":0.9657999873161316,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10972","display_name":"Power Systems Fault Detection","score":0.9620000123977661,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.8299169540405273},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6538171172142029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6297287940979004},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6114404201507568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37619760632514954},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18779915571212769},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.06682682037353516}],"concepts":[{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.8299169540405273},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6538171172142029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6297287940979004},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6114404201507568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37619760632514954},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18779915571212769},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.06682682037353516},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc59868.2024.10850369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc59868.2024.10850369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Performance, Computing, and Communications Conference (IPCCC)","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":11,"referenced_works":["https://openalex.org/W2923014074","https://openalex.org/W2963323070","https://openalex.org/W2979691890","https://openalex.org/W3106070274","https://openalex.org/W3136363192","https://openalex.org/W3174657338","https://openalex.org/W6755207826","https://openalex.org/W6768851824","https://openalex.org/W6776767859","https://openalex.org/W6810362000","https://openalex.org/W6850764752"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081982437","https://openalex.org/W4394857231","https://openalex.org/W2027050655","https://openalex.org/W3028244590","https://openalex.org/W4254349500","https://openalex.org/W2014369232","https://openalex.org/W3122042562"],"abstract_inverted_index":{"Transformer":[0,38],"models":[1,135],"have":[2],"achieved":[3],"significant":[4,146],"success":[5],"in":[6,167],"various":[7],"complex":[8],"tasks,":[9],"but":[10],"their":[11],"high":[12],"computational":[13],"costs":[14],"and":[15,65,114,123,139],"longer":[16],"inference":[17],"latency":[18],"serve":[19],"as":[20,33],"limiting":[21],"factors.":[22],"To":[23,83],"effectively":[24,124],"reduce":[25],"these":[26,51,85],"costs,":[27],"pruning":[28,43,49,95,175],"has":[29],"been":[30],"widely":[31],"adopted":[32],"an":[34,164],"efficient":[35],"method":[36,131],"for":[37],"models.":[39],"Despite":[40],"the":[41,60,77,81,137,150],"excellent":[42],"speed":[44],"demonstrated":[45],"by":[46],"existing":[47,173],"retraining-free":[48,93,174],"algorithms,":[50],"methods":[52],"often":[53],"only":[54],"find":[55,125],"local":[56],"optima":[57],"when":[58],"assessing":[59],"importance":[61],"of":[62,80,106],"attention":[63],"heads":[64],"feed-forward":[66],"networks.":[67],"This":[68],"limitation":[69],"may":[70],"lead":[71],"to":[72,121],"unstable":[73],"solutions,":[74],"thus":[75],"affecting":[76],"overall":[78],"performance":[79],"model.":[82],"address":[84],"challenges,":[86],"we":[87],"propose":[88],"DP-Prune":[89,162],"(Dynamic":[90,110],"Programming-Prune),":[91],"a":[92,99,158],"structured":[94],"algorithm":[96,104],"that":[97],"employs":[98],"global":[100,126],"optimization":[101],"strategy.":[102],"The":[103],"consists":[105],"two":[107],"parts:":[108],"DPMO":[109],"Programming":[111],"Mask":[112,118],"Optimization)":[113],"GSMT":[115],"(GCROTMK":[116],"Solver":[117],"Tuning),":[119],"designed":[120],"quickly":[122],"optima.":[127],"We":[128],"evaluate":[129],"this":[130],"using":[132],"BERTBASEand":[133],"DistilBERT":[134],"on":[136,149],"GLUE":[138],"SQuAD":[140],"benchmark":[141],"tests.":[142],"Experimental":[143],"results":[144],"demonstrate":[145],"accuracy":[147],"improvements":[148],"SQuAD2.0task":[151],"test":[152],"without":[153],"any":[154],"further":[155],"training.":[156],"Under":[157],"60%":[159],"FLOPs":[160],"constraint,":[161],"achieves":[163],"8.42%":[165],"increase":[166],"F1":[168],"score":[169],"compared":[170],"with":[171],"some":[172],"algorithms.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}