{"id":"https://openalex.org/W7151562130","doi":"https://doi.org/10.1109/icmla66185.2025.00053","title":"Privacy-Preserving Model Compression: Adaptive Pruning for Federated Split Learning of LLMs","display_name":"Privacy-Preserving Model Compression: Adaptive Pruning for Federated Split Learning of LLMs","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7151562130","doi":"https://doi.org/10.1109/icmla66185.2025.00053"},"language":null,"primary_location":{"id":"doi:10.1109/icmla66185.2025.00053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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/A5066122753","display_name":"Dinesh Chowdary Attota","orcid":"https://orcid.org/0000-0001-8873-0363"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dinesh Chowdary Attota","raw_affiliation_strings":["Kennesaw State University,CCSE,Marietta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Kennesaw State University,CCSE,Marietta,GA,USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103189799","display_name":"Linh Le","orcid":"https://orcid.org/0000-0002-0087-3448"},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dr. Linh Le","raw_affiliation_strings":["Kennesaw State University,CCSE,Marietta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Kennesaw State University,CCSE,Marietta,GA,USA","institution_ids":["https://openalex.org/I172980758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133084733","display_name":"Ying Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I172980758","display_name":"Kennesaw State University","ror":"https://ror.org/00jeqjx33","country_code":"US","type":"education","lineage":["https://openalex.org/I172980758"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Xie","raw_affiliation_strings":["Kennesaw State University,CCSE,Marietta,GA,USA"],"affiliations":[{"raw_affiliation_string":"Kennesaw State University,CCSE,Marietta,GA,USA","institution_ids":["https://openalex.org/I172980758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066122753"],"corresponding_institution_ids":["https://openalex.org/I172980758"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8729344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9581000208854675,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9581000208854675,"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/T10237","display_name":"Cryptography and Data Security","score":0.013199999928474426,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.007499999832361937,"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":0.5340999960899353},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37869998812675476},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27799999713897705},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.26440000534057617},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24009999632835388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187999844551086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5569999814033508},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4072999954223633},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24009999632835388},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.23440000414848328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmla66185.2025.00053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00053","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","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":20,"referenced_works":["https://openalex.org/W2914397182","https://openalex.org/W2977090839","https://openalex.org/W2995022099","https://openalex.org/W3086809868","https://openalex.org/W3210225643","https://openalex.org/W4321483947","https://openalex.org/W4393147854","https://openalex.org/W4401857637","https://openalex.org/W4401863415","https://openalex.org/W4401863519","https://openalex.org/W4403125117","https://openalex.org/W4404783584","https://openalex.org/W4406207083","https://openalex.org/W4406457499","https://openalex.org/W4409798136","https://openalex.org/W4411119784","https://openalex.org/W4412130408","https://openalex.org/W4415799087","https://openalex.org/W7133245307","https://openalex.org/W7148786437"],"related_works":[],"abstract_inverted_index":{"The":[0],"deployment":[1],"of":[2,76,148,161,166],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"on":[7],"devices":[8],"with":[9],"limited":[10],"resources":[11],"faces":[12],"significant":[13],"challenges":[14],"due":[15],"to":[16,34,57],"their":[17],"high":[18,120],"computational":[19],"and":[20,61,78,90,133,145,158],"memory":[21],"requirements,":[22],"further":[23],"complicated":[24],"by":[25,72,128],"privacy":[26,97],"issues":[27],"in":[28,152],"decentralized":[29],"training":[30],"settings.":[31,139],"In":[32,104],"response":[33],"these":[35],"challenges,":[36],"we":[37],"introduce":[38],"an":[39],"innovative":[40],"framework":[41,112],"that":[42,67],"combines":[43],"a":[44,49,65,99],"Adaptive":[45],"Pruning":[46],"Algorithm":[47],"within":[48],"Federated":[50],"Split":[51],"Learning":[52],"architecture,":[53],"utilizing":[54],"dynamic":[55],"sparsity":[56,126],"enhance":[58],"both":[59,87],"performance":[60],"efficiency.":[62],"We":[63],"employ":[64],"method":[66],"actively":[68],"reduces":[69],"model":[70,88,101],"weights":[71],"assessing":[73],"the":[74,108,111,143,159,164],"significance":[75],"activation":[77],"gradient,":[79],"incorporating":[80],"bias":[81],"correction.":[82],"This":[83,140],"strategy":[84],"notably":[85],"decreases":[86],"size":[89],"communication":[91],"demands,":[92],"all":[93],"while":[94],"maintaining":[95],"data":[96],"via":[98],"client-server":[100],"partitioning":[102],"approach.":[103],"our":[105],"evaluation":[106],"using":[107],"E2ENLG":[109],"dataset,":[110],"demonstrates":[113],"exceptional":[114],"performance,":[115],"achieving":[116],"METEOR":[117],"scores":[118],"as":[119,121,129,131,156],"0.9256.":[122],"It":[123],"surpasses":[124],"fixed":[125],"methods":[127],"much":[130],"25%":[132],"showcases":[134],"impressive":[135],"scalability":[136],"across":[137],"various":[138],"study":[141],"facilitates":[142],"effective":[144],"privacy-conscious":[146],"implementation":[147],"large":[149],"language":[150],"models":[151],"resource-constrained":[153],"environments":[154],"such":[155],"healthcare":[157],"Internet":[160],"Things,":[162],"promoting":[163],"advancement":[165],"accessible":[167],"artificial":[168],"intelligence":[169],"solutions.":[170]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2026-04-08T00:00:00"}