{"id":"https://openalex.org/W6929650186","doi":"https://doi.org/10.48550/arxiv.2508.09471","title":"EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models","display_name":"EGGS-PTP: An Expander-Graph Guided Structured Post-training Pruning Method for Large Language Models","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W6929650186","doi":"https://doi.org/10.48550/arxiv.2508.09471"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2508.09471","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.09471","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2508.09471","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bazarbachi, Omar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bazarbachi, Omar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sun, Zijun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Shen, Yanning","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Yanning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10422","display_name":"Angiogenesis and VEGF in Cancer","score":0.695900022983551,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10422","display_name":"Angiogenesis and VEGF in Cancer","score":0.695900022983551,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11190","display_name":"3D Printing in Biomedical Research","score":0.02889999933540821,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T10771","display_name":"Wound Healing and Treatments","score":0.014299999922513962,"subfield":{"id":"https://openalex.org/subfields/2742","display_name":"Rehabilitation"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.8385000228881836},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6220999956130981},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44190001487731934},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4108000099658966},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.35920000076293945},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.3580000102519989},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.303600013256073}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8385000228881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7932999730110168},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6220999956130981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5491999983787537},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5425999760627747},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27900001406669617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2779136372","wikidata":"https://www.wikidata.org/wiki/Q10283002","display_name":"Information flow","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2508.09471","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.09471","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2508.09471","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.09471","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"become":[5],"more":[6,37],"widely":[7],"adopted":[8],"and":[9,16,75,107],"scale":[10],"up":[11],"in":[12,20,121],"size,":[13],"the":[14,32,45,65,89],"computational":[15,76],"memory":[17,108],"challenges":[18],"involved":[19],"deploying":[21],"these":[22],"massive":[23],"foundation":[24],"models":[25],"have":[26],"grown":[27],"increasingly":[28],"severe.":[29],"This":[30],"underscores":[31],"urgent":[33],"need":[34],"to":[35,63,111],"develop":[36],"efficient":[38],"model":[39,73,94],"variants.":[40],"Faced":[41],"with":[42],"this":[43],"challenge,":[44],"present":[46],"work":[47],"introduces":[48],"EGGS-PTP:":[49],"an":[50],"Expander-Graph":[51],"Guided":[52],"Structured":[53],"Post-training":[54],"Pruning":[55],"method.":[56],"The":[57],"proposed":[58],"approach":[59],"leverages":[60],"graph":[61],"theory":[62],"guide":[64],"design":[66],"of":[67,123],"N:M":[68],"structured":[69,112,118],"pruning,":[70],"effectively":[71],"reducing":[72],"size":[74],"demands.":[77],"By":[78],"incorporating":[79],"concepts":[80],"from":[81],"expander":[82],"graphs,":[83],"EGGS-PTP":[84,101],"ensures":[85],"information":[86],"flow":[87],"within":[88],"pruned":[90],"network,":[91],"preserving":[92],"essential":[93],"functionality.":[95],"Extensive":[96],"numerical":[97],"experiments":[98],"demonstrate":[99],"that":[100],"not":[102],"only":[103],"achieves":[104],"significant":[105],"acceleration":[106],"savings":[109],"due":[110],"sparsity":[113],"but":[114],"also":[115],"outperforms":[116],"existing":[117],"pruning":[119],"techniques":[120],"terms":[122],"accuracy":[124],"across":[125],"various":[126],"LLMs.":[127]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}