{"id":"https://openalex.org/W4282968244","doi":"https://doi.org/10.1145/3524059.3532366","title":"PAME","display_name":"PAME","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4282968244","doi":"https://doi.org/10.1145/3524059.3532366"},"language":"en","primary_location":{"id":"doi:10.1145/3524059.3532366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524059.3532366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th ACM International Conference on Supercomputing","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/A5012349805","display_name":"Shulai Zhang","orcid":"https://orcid.org/0000-0002-0802-7203"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shulai Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008837660","display_name":"Weihao Cui","orcid":"https://orcid.org/0000-0002-6646-5260"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihao Cui","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060235293","display_name":"Zhengnian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengnian Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114626347","display_name":"Yue Guan","orcid":"https://orcid.org/0000-0001-7773-4588"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Guan","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675801","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-2259-196X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5012349805"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.5031,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.62605293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/computer-science","display_name":"Computer science","score":0.7569308876991272},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6165647506713867},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5697320103645325},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4352877140045166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3239704966545105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569308876991272},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6165647506713867},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5697320103645325},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4352877140045166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3239704966545105},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524059.3532366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524059.3532366","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1676314349","https://openalex.org/W2080873731","https://openalex.org/W2108598243","https://openalex.org/W2118978333","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2565600385","https://openalex.org/W2565639579","https://openalex.org/W2739542029","https://openalex.org/W2767421475","https://openalex.org/W2798291715","https://openalex.org/W2886439381","https://openalex.org/W2944701285","https://openalex.org/W2962677625","https://openalex.org/W2962944050","https://openalex.org/W2963393494","https://openalex.org/W2963402313","https://openalex.org/W2976122994","https://openalex.org/W2981812042","https://openalex.org/W2995751512","https://openalex.org/W3005664618","https://openalex.org/W3012554562","https://openalex.org/W3014641072","https://openalex.org/W3033737024","https://openalex.org/W3035030897","https://openalex.org/W3035038672","https://openalex.org/W3101163004","https://openalex.org/W3130607817","https://openalex.org/W3204009762","https://openalex.org/W3208262036","https://openalex.org/W3208777667","https://openalex.org/W4212986322","https://openalex.org/W4235578650","https://openalex.org/W6947880523"],"related_works":["https://openalex.org/W2779562428","https://openalex.org/W3008625068","https://openalex.org/W1987753576","https://openalex.org/W4379251913","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3033499831","https://openalex.org/W4296285654","https://openalex.org/W2380362089","https://openalex.org/W4385812565"],"abstract_inverted_index":{"In":[0],"emerging":[1],"DNN":[2,47,55,96,122,149],"serving":[3],"systems,":[4],"queries":[5,17,37,58],"are":[6],"usually":[7],"batched":[8],"to":[9,33,40,49,82,92,114,120],"fully":[10],"leverage":[11],"hardware":[12],"resources,":[13],"and":[14,26,98,111,124],"all":[15],"the":[16,23,29,46,69,84,104,138,146],"in":[18,53,68],"a":[19,43,54,72,89,94,99],"batch":[20],"run":[21],"through":[22,42],"complete":[24],"model":[25,48,97],"return":[27,66],"at":[28],"same":[30],"time.":[31],"According":[32],"our":[34],"findings,":[35],"some":[36],"only":[38],"need":[39],"pass":[41],"portion":[44],"of":[45,71,103,145],"attain":[50],"sufficient":[51],"precision":[52,144],"service.":[56],"These":[57],"can":[59,65],"have":[60],"shorter":[61],"latencies":[62],"if":[63],"they":[64],"early":[67],"middle":[70],"model.":[73],"Therefore,":[74],"we":[75],"propose":[76],"precision-aware":[77],"multi-exit":[78,95],"inference":[79,105],"serving,":[80],"PAME,":[81],"achieve":[83],"above":[85],"purpose.":[86],"PAME":[87,117,131],"provides":[88],"holistic":[90],"scheme":[91],"build":[93],"corresponding":[100],"system-level":[101],"design":[102],"engine.":[106],"We":[107],"use":[108],"representative":[109],"CV":[110],"NLP":[112],"benchmarks":[113],"evaluate":[115],"PAME.":[116],"is":[118],"adaptive":[119],"various":[121],"tasks":[123],"service":[125],"loads.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"reduces":[132],"39.9%":[133],"average":[134],"latency":[135],"without":[136],"increasing":[137],"tail":[139],"latency,":[140],"while":[141],"maintaining":[142],"99.68%":[143],"original":[147],"single-exit":[148],"models":[150],"on":[151],"average.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-06-17T00:00:00"}