{"id":"https://openalex.org/W4405253937","doi":"https://doi.org/10.1109/infocom55648.2025.11044536","title":"Harpagon: Minimizing DNN Serving Cost via Efficient Dispatching, Scheduling and Splitting","display_name":"Harpagon: Minimizing DNN Serving Cost via Efficient Dispatching, Scheduling and Splitting","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4405253937","doi":"https://doi.org/10.1109/infocom55648.2025.11044536"},"language":"en","primary_location":{"id":"doi:10.1109/infocom55648.2025.11044536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.06161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100531724","display_name":"Zhixin Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Zhao","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792327","display_name":"Yitao Hu","orcid":"https://orcid.org/0009-0004-0458-0900"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yitao Hu","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziqi Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqi Gong","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101862689","display_name":"Guotao Yang","orcid":"https://orcid.org/0000-0003-1885-0305"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guotao Yang","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397201","display_name":"Wenxin Li","orcid":"https://orcid.org/0000-0001-5705-9650"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Li","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009324770","display_name":"Xiulong Liu","orcid":"https://orcid.org/0000-0002-4746-5599"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiulong Liu","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474713","display_name":"Keqiu Li","orcid":"https://orcid.org/0000-0002-3534-1126"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keqiu Li","raw_affiliation_strings":["Tianjin University,Tianjin Key Laboratory of Advanced Networking,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University,Tianjin Key Laboratory of Advanced Networking,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015014802","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0001-9499-8446"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Wang","raw_affiliation_strings":["Stevens Institute of Technology,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stevens Institute of Technology,USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00118862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9682999849319458,"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"}},"topics":[{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9682999849319458,"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"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9498000144958496,"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"}},{"id":"https://openalex.org/T11932","display_name":"Wireless Body Area Networks","score":0.9380999803543091,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6204969882965088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6054507493972778},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.36341190338134766},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.3467998504638672},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33076098561286926},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3089495897293091},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15531155467033386}],"concepts":[{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6204969882965088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6054507493972778},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36341190338134766},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3467998504638672},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33076098561286926},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3089495897293091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15531155467033386}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/infocom55648.2025.11044536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom55648.2025.11044536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2025 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.06161","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.06161","pdf_url":"https://arxiv.org/pdf/2412.06161","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.06161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.06161","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":"pmh:oai:arXiv.org:2412.06161","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.06161","pdf_url":"https://arxiv.org/pdf/2412.06161","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3404210196","display_name":null,"funder_award_id":"62202328","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6975830235","display_name":null,"funder_award_id":"2022YFB4501000","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"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":0,"referenced_works":[],"related_works":["https://openalex.org/W2115140794","https://openalex.org/W2041120224","https://openalex.org/W1504320321","https://openalex.org/W2067902980","https://openalex.org/W2548529098","https://openalex.org/W4312275919","https://openalex.org/W2338293335","https://openalex.org/W2039378765","https://openalex.org/W2614685449","https://openalex.org/W283879968"],"abstract_inverted_index":{"Advances":[0],"in":[1,22,164],"deep":[2],"neural":[3],"networks":[4],"(DNNs)":[5],"have":[6],"significantly":[7],"contributed":[8],"to":[9,28,68,109,140,161,174],"the":[10,70,86,99,111,117,133,142,154,157,169,175,184],"development":[11],"of":[12,19,126,156,187],"real-time":[13],"video":[14],"processing":[15],"applications.":[16,148],"Efficient":[17],"scheduling":[18],"DNN":[20,79],"workloads":[21,192],"cloud-hosted":[23],"inference":[24,80],"systems":[25,39],"is":[26],"crucial":[27],"minimizing":[29],"serving":[30,71,87,144,165,188],"costs":[31],"while":[32,167],"meeting":[33],"application":[34],"latency":[35,44,56,59,90,135,138,170],"constraints.":[36],"However,":[37],"existing":[38],"suffer":[40],"from":[41],"excessive":[42],"module":[43,52,112,118],"during":[45,51,58],"request":[46,106],"dispatching,":[47],"low":[48],"execution":[49],"throughput":[50,119],"scheduling,":[53],"and":[54,123],"wasted":[55],"budget":[57,139],"splitting":[60],"for":[61,146,190],"multi-DNN":[62,147],"applications,":[63],"which":[64,84],"undermines":[65],"their":[66],"capability":[67],"minimize":[69,110,141],"cost.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"design":[77],"a":[78,93,104],"system":[81],"called":[82],"Harpagon,":[83],"minimizes":[85],"cost":[88,145,166,189],"under":[89],"constraints":[91],"with":[92,103,120,193],"three-level":[94],"design.":[95],"It":[96,114,129],"first":[97],"maximizes":[98,116],"batch":[100],"collection":[101],"rate":[102],"batch-aware":[105],"dispatch":[107],"policy":[108],"latency.":[113],"then":[115],"multi-tuple":[121],"configurations":[122],"proper":[124],"amount":[125],"dummy":[127],"requests.":[128],"also":[130],"carefully":[131],"splits":[132],"end-to-end":[134],"into":[136],"per-module":[137],"total":[143],"Evaluation":[149],"shows":[150],"that":[151],"Harpagon":[152,182],"outperforms":[153],"state":[155],"art":[158],"by":[159],"1.49":[160],"2.37":[162],"times":[163],"satisfying":[168],"objectives.":[171],"Additionally,":[172],"compared":[173],"optimal":[176],"solution":[177],"using":[178],"brute":[179],"force":[180],"search,":[181],"derives":[183],"lower":[185],"bound":[186],"91.5%":[191],"millisecond":[194],"level":[195],"runtime.":[196]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-12-12T00:00:00"}
