{"id":"https://openalex.org/W7124140394","doi":"https://doi.org/10.1109/icpads67057.2025.11323095","title":"FUPS: Fusion-Based Parallel Structured Pruning for Large Language Models","display_name":"FUPS: Fusion-Based Parallel Structured Pruning for Large Language Models","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124140394","doi":"https://doi.org/10.1109/icpads67057.2025.11323095"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5094189928","display_name":"Shouyuan Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165606","display_name":"Hubei Normal University","ror":"https://ror.org/056y3dw16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouyuan Qin","raw_affiliation_strings":["Hubei Normal University,Huangshi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Normal University,Huangshi,China","institution_ids":["https://openalex.org/I4210165606"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088598702","display_name":"Guixia Wang","orcid":"https://orcid.org/0000-0001-8107-616X"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guixia Wang","raw_affiliation_strings":["South China Normal University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China Normal University,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072709173","display_name":"Xuhui Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165606","display_name":"Hubei Normal University","ror":"https://ror.org/056y3dw16","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165606"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhui Xiong","raw_affiliation_strings":["Hubei Normal University,Huangshi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei Normal University,Huangshi,China","institution_ids":["https://openalex.org/I4210165606"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.499099999666214,"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":0.499099999666214,"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/T10028","display_name":"Topic Modeling","score":0.08799999952316284,"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":0.03869999945163727,"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/pruning","display_name":"Pruning","score":0.6327999830245972},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5566999912261963},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5403000116348267},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4075999855995178},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4052000045776367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756600022315979},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6327999830245972},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5403000116348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45969998836517334},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4250999987125397},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30079999566078186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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":22,"referenced_works":["https://openalex.org/W1967810725","https://openalex.org/W1998336350","https://openalex.org/W2963363373","https://openalex.org/W2969388332","https://openalex.org/W2991040477","https://openalex.org/W2994881943","https://openalex.org/W2997006708","https://openalex.org/W3015735225","https://openalex.org/W3129831491","https://openalex.org/W3132015947","https://openalex.org/W3132107458","https://openalex.org/W3204998121","https://openalex.org/W4393147854","https://openalex.org/W4400680808","https://openalex.org/W4402350363","https://openalex.org/W4405934565","https://openalex.org/W4411309330","https://openalex.org/W4415796952","https://openalex.org/W4415798574","https://openalex.org/W4415798754","https://openalex.org/W4415799087","https://openalex.org/W4415799245"],"related_works":[],"abstract_inverted_index":{"Model":[0],"pruning":[1,32,61],"is":[2,69,170],"an":[3],"effective":[4],"technique":[5],"to":[6,36,49,74,93],"reduce":[7],"the":[8,110,119,124,130,141],"dependency":[9],"of":[10,113,129],"neural":[11],"networks":[12],"on":[13,137,164],"hardware":[14],"resources":[15],"while":[16],"maintaining":[17],"their":[18],"performance,":[19],"especially":[20],"for":[21],"Large":[22],"Language":[23],"Models(LLMs)":[24],"with":[25],"ever-increasing":[26],"parameter":[27],"scales.":[28],"However,":[29],"existing":[30,156],"structured":[31,60],"methods":[33,157],"often":[34],"struggle":[35],"retain":[37],"satisfactory":[38],"performance":[39,149],"under":[40],"high":[41],"sparsity":[42,152],"ratios":[43],"and":[44,72,98,126,140,154,162],"exhibit":[45],"inefficiencies":[46],"when":[47],"applied":[48],"ultra-large":[50],"models.":[51],"To":[52],"address":[53],"these":[54],"limitations,":[55],"we":[56],"propose":[57],"a":[58,84,105],"novel":[59],"algorithm,":[62],"Fusion-Based":[63],"Parallel":[64],"Structured":[65],"Pruning":[66],"(FUPS),":[67],"which":[68],"simple,":[70],"efficient,":[71],"easy":[73],"deploy.":[75],"Its":[76],"effectiveness":[77],"stems":[78],"from":[79],"two":[80],"key":[81],"innovations:":[82],"(1)":[83],"block-wise":[85],"mechanism":[86,107],"that":[87,108,144],"partitions":[88],"matrices":[89],"into":[90],"smaller":[91],"sub-blocks":[92],"enable":[94],"finer-grained":[95],"redundancy":[96],"identification":[97],"enhance":[99],"parallel":[100],"processing":[101],"across":[102,150],"accelerators;":[103],"(2)":[104],"fusion":[106],"mitigates":[109],"adverse":[111],"impact":[112],"knowledge":[114],"space":[115],"fragmentation":[116],"introduced":[117],"by":[118],"block":[120],"mechanism,":[121],"thereby":[122],"enhancing":[123],"robustness":[125],"generalization":[127],"capability":[128],"matrix":[131],"representation.":[132],"We":[133],"conduct":[134],"extensive":[135],"experiments":[136],"various":[138],"models,":[139],"results":[142],"show":[143],"FUPS":[145],"consistently":[146],"preserves":[147],"model":[148],"different":[151],"settings":[153],"outperforms":[155],"such":[158],"as":[159],"LLMPruner,":[160],"Wanda,":[161],"FLAP":[163],"multiple":[165],"benchmark":[166],"tasks.":[167],"The":[168],"code":[169],"released":[171],"at":[172],"https://github.com/Qsiny/FUPS.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-15T00:00:00"}