{"id":"https://openalex.org/W4414169970","doi":"https://doi.org/10.1109/iwqos65803.2025.11143488","title":"Malva: A Jitter-Aware Online Pruning Framework for DNN Inference Tasks","display_name":"Malva: A Jitter-Aware Online Pruning Framework for DNN Inference Tasks","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414169970","doi":"https://doi.org/10.1109/iwqos65803.2025.11143488"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","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/A5045410502","display_name":"Ziyan Fu","orcid":"https://orcid.org/0000-0002-1039-0386"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Fu","raw_affiliation_strings":["BNRist, Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037386169","display_name":"Yongheng Deng","orcid":"https://orcid.org/0000-0003-3010-3812"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongheng Deng","raw_affiliation_strings":["BNRist, Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101847187","display_name":"Li Li","orcid":"https://orcid.org/0000-0002-2803-3803"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Co., Ltd.,Department of Platform Product,Suzhou,China,215000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Co., Ltd.,Department of Platform Product,Suzhou,China,215000","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107518675","display_name":"Yingjun Wu","orcid":"https://orcid.org/0009-0008-9880-4301"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjun Wu","raw_affiliation_strings":["China Mobile (Suzhou) Software Technology Co., Ltd.,Department of Platform Product,Suzhou,China,215000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile (Suzhou) Software Technology Co., Ltd.,Department of Platform Product,Suzhou,China,215000","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100422345","display_name":"Zhibo Wang","orcid":"https://orcid.org/0000-0002-5804-3279"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibo Wang","raw_affiliation_strings":["Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China,310000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,The State Key Laboratory of Blockchain and Data Security,Hangzhou,China,310000","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034995427","display_name":"Su Yao","orcid":"https://orcid.org/0000-0001-5165-2787"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Su Yao","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000488023","display_name":"Yaoxue Zhang","orcid":"https://orcid.org/0000-0002-4833-9789"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoxue Zhang","raw_affiliation_strings":["BNRist, Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015419107","display_name":"Ju Ren","orcid":"https://orcid.org/0000-0003-2782-183X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Ren","raw_affiliation_strings":["BNRist, Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNRist, Tsinghua University,Department of Computer Science and Technology,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"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":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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":0.9976999759674072,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9950000047683716,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8019000291824341},{"id":"https://openalex.org/keywords/jitter","display_name":"Jitter","score":0.7766000032424927},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6574000120162964},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6319000124931335},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5559999942779541},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.4771000146865845},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45179998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518999814987183},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8019000291824341},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.7766000032424927},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6574000120162964},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6319000124931335},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.4771000146865845},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45179998874664307},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39259999990463257},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143488","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3811302298","display_name":null,"funder_award_id":"62402268,62432004,U24B20182,U22B2031,62472240","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5185231776","display_name":null,"funder_award_id":"2022YFF0604502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6463385185","display_name":null,"funder_award_id":"2023M741947","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1690739335","https://openalex.org/W2194775991","https://openalex.org/W2595827304","https://openalex.org/W2885579974","https://openalex.org/W2896457183","https://openalex.org/W2908906661","https://openalex.org/W2923014074","https://openalex.org/W2962677625","https://openalex.org/W3034251466","https://openalex.org/W3034368386","https://openalex.org/W3035038672","https://openalex.org/W3118608800","https://openalex.org/W3138154797","https://openalex.org/W3165698711","https://openalex.org/W3168652588","https://openalex.org/W3184606595","https://openalex.org/W4200171683","https://openalex.org/W4210548837","https://openalex.org/W4285243442","https://openalex.org/W4297950276","https://openalex.org/W4309263372","https://openalex.org/W4367044888","https://openalex.org/W4386607611","https://openalex.org/W4390306248","https://openalex.org/W4392173870","https://openalex.org/W4392908745","https://openalex.org/W4398756379","https://openalex.org/W4400876897","https://openalex.org/W4404400716"],"related_works":[],"abstract_inverted_index":{"In":[0],"fields":[1],"like":[2],"autonomous":[3],"driving,":[4],"strict":[5],"constraints":[6],"are":[7],"imposed":[8],"on":[9,20,94],"the":[10,55,69,101,118,123,147,173,178],"computing":[11,56,60],"latency":[12,42,61],"of":[13,150],"deep":[14],"neural":[15],"network":[16],"(DNN)":[17],"inference":[18],"tasks":[19,33],"edge":[21,28],"servers.":[22],"However,":[23],"it":[24],"is":[25],"typical":[26],"for":[27,81,85],"servers":[29],"to":[30,36,45,67,113,125,132,145,176],"execute":[31],"multiple":[32,38],"in":[34,187],"parallel":[35],"serve":[37],"users,":[39],"causing":[40],"severe":[41],"jitter":[43,57,95,135],"due":[44],"resource":[46],"competition,":[47],"which":[48],"seriously":[49],"affects":[50],"timeliness.":[51],"Existing":[52],"works":[53],"ignore":[54],"and":[58,106,110,134,170],"regard":[59],"as":[62],"a":[63,79,140,165],"deterministic":[64],"value,":[65],"failing":[66],"meet":[68],"timeliness":[70],"requirement.":[71],"To":[72],"address":[73],"this":[74],"issue,":[75],"we":[76,138],"propose":[77,139],"Malva,":[78],"framework":[80],"finegrained":[82],"online":[83],"pruning":[84,90,111],"DNN":[86,102],"tasks,":[87],"allowing":[88],"flexible":[89],"at":[91],"runtime":[92],"based":[93],"conditions.":[96,136],"Specifically,":[97],"Malva":[98,119,161],"first":[99,179],"partitions":[100],"model":[103],"into":[104],"blocks":[105],"applies":[107],"early":[108,130],"exiting":[109],"methods":[112,186],"create":[114],"block":[115],"variants.":[116],"Then,":[117],"scheduler":[120],"flexibly":[121],"selects":[122],"variant":[124],"be":[126],"executed":[127],"or":[128],"exits":[129],"according":[131],"urgency":[133],"Moreover,":[137],"novel":[141],"urgency-aware":[142],"prediction":[143],"strategy":[144],"estimate":[146],"accuracy":[148],"impact":[149],"variants":[151],"with":[152],"incomplete":[153],"pathway":[154],"information":[155],"during":[156],"scheduling.":[157],"Stress":[158],"testing":[159],"shows":[160],"can":[162],"strictly":[163],"maintain":[164],"zero":[166],"deadline":[167,180],"miss":[168,181],"rate":[169],"significantly":[171],"increase":[172],"stress":[174],"required":[175],"cause":[177],"while":[182],"still":[183],"outperforming":[184],"state-of-the-art":[185],"accuracy.":[188]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}