{"id":"https://openalex.org/W7080129495","doi":"https://doi.org/10.48550/arxiv.2509.04244","title":"Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression","display_name":"Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression","publication_year":2025,"publication_date":"2025-09-04","ids":{"openalex":"https://openalex.org/W7080129495","doi":"https://doi.org/10.48550/arxiv.2509.04244"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2509.04244","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.04244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2509.04244","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Makenali, Sara","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Makenali, Sara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rokh, Babak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rokh, Babak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Azarpeyvand, Ali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Azarpeyvand, Ali","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6258999705314636,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6258999705314636,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.028300000354647636,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.024399999529123306,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.8075000047683716},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6672000288963318},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5564000010490417},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4602999985218048},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4325999915599823},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.382999986410141},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.34200000762939453}],"concepts":[{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.8075000047683716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473999857902527},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6672000288963318},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4602999985218048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44589999318122864},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4325999915599823},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3912000060081482},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.3154999911785126},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.3149000108242035},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2509.04244","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.04244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2509.04244","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.04244","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"},"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":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4],"achieved":[5],"significant":[6],"advances":[7],"in":[8,34,56],"a":[9,21,89],"wide":[10],"range":[11],"of":[12,28,104,163],"applications.":[13],"However,":[14],"their":[15,85,95],"deployment":[16,189],"on":[17,98,190],"resource-constrained":[18],"devices":[19,191],"remains":[20],"challenge":[22],"due":[23,93],"to":[24,59,83,94,126,155],"the":[25,102,136,148,164],"large":[26],"number":[27],"layers":[29],"and":[30,37,45,63,81,101,140],"parameters,":[31,159],"which":[32],"result":[33],"considerable":[35],"computational":[36,194],"memory":[38],"demands.":[39],"To":[40],"address":[41],"this":[42,110],"issue,":[43],"pruning":[44,80,120,139,151],"quantization":[46,82,125,141,162],"are":[47,142],"two":[48,70,114],"widely":[49],"used":[50],"compression":[51,76,129,180],"techniques,":[52],"commonly":[53],"applied":[54,143],"individually":[55],"most":[57],"studies":[58],"reduce":[60],"model":[61,99,133,166,179],"size":[62],"enhance":[64],"processing":[65],"speed.":[66],"Nevertheless,":[67],"combining":[68],"these":[69],"techniques":[71],"can":[72],"yield":[73],"even":[74],"greater":[75],"benefits.":[77],"Effectively":[78],"integrating":[79],"harness":[84],"complementary":[86],"advantages":[87],"poses":[88],"challenging":[90],"task,":[91],"primarily":[92],"potential":[96],"impact":[97],"accuracy":[100,183],"complexity":[103],"jointly":[105],"optimizing":[106],"both":[107],"processes.":[108],"In":[109,135,147],"paper,":[111],"we":[112],"propose":[113],"approaches":[115,176],"that":[116,173],"integrate":[117],"similarity-based":[118],"filter":[119],"with":[121,181,192],"Adaptive":[122],"Power-of-Two":[123],"(APoT)":[124],"achieve":[127,177],"higher":[128],"efficiency":[130],"while":[131],"preserving":[132],"accuracy.":[134],"first":[137,154],"approach,":[138,150],"simultaneously":[144],"during":[145],"training.":[146],"second":[149],"is":[152],"performed":[153],"remove":[156],"less":[157],"important":[158],"followed":[160],"by":[161],"pruned":[165],"using":[167],"low-bit":[168],"representations.":[169],"Experimental":[170],"results":[171],"demonstrate":[172],"our":[174],"proposed":[175],"effective":[178],"minimal":[182],"degradation,":[184],"making":[185],"them":[186],"well-suited":[187],"for":[188],"limited":[193],"resources.":[195]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}