{"id":"https://openalex.org/W4413178996","doi":"https://doi.org/10.1109/gcwkshp64532.2024.11100386","title":"Enhancing Latency-Accuracy Tradeoff in Dynamic Split Inference via Vector Quantized Bottleneck","display_name":"Enhancing Latency-Accuracy Tradeoff in Dynamic Split Inference via Vector Quantized Bottleneck","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4413178996","doi":"https://doi.org/10.1109/gcwkshp64532.2024.11100386"},"language":"en","primary_location":{"id":"doi:10.1109/gcwkshp64532.2024.11100386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshp64532.2024.11100386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Globecom Workshops (GC Wkshps)","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/A5038195714","display_name":"Chen Yen-Hsiu","orcid":null},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Chen Yen-Hsiu","raw_affiliation_strings":["Yokohama National University,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Yokohama National University,Yokohama,Japan","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102468628","display_name":"Yoichi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoichi Hirose","raw_affiliation_strings":["Yokohama National University,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Yokohama National University,Yokohama,Japan","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048988754","display_name":"Shoma Shimizu","orcid":null},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoma Shimizu","raw_affiliation_strings":["Yokohama National University,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Yokohama National University,Yokohama,Japan","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078648227","display_name":"Shota Saito","orcid":"https://orcid.org/0000-0002-9863-6765"},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Saito","raw_affiliation_strings":["Yokohama National University,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Yokohama National University,Yokohama,Japan","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048507108","display_name":"Kento Uchida","orcid":"https://orcid.org/0000-0002-4179-6020"},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kento Uchida","raw_affiliation_strings":["Yokohama National University,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Yokohama National University,Yokohama,Japan","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005268349","display_name":"Shinichi Shirakawa","orcid":"https://orcid.org/0000-0002-4659-6108"},"institutions":[{"id":"https://openalex.org/I180203408","display_name":"Yokohama National University","ror":"https://ror.org/03zyp6p76","country_code":"JP","type":"education","lineage":["https://openalex.org/I180203408"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinichi Shirakawa","raw_affiliation_strings":["Yokohama National University,Yokohama,Japan"],"affiliations":[{"raw_affiliation_string":"Yokohama National University,Yokohama,Japan","institution_ids":["https://openalex.org/I180203408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042195263","display_name":"Takayuki Nishio","orcid":"https://orcid.org/0000-0003-1026-319X"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takayuki Nishio","raw_affiliation_strings":["Tokyo Institute of Technology,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology,Tokyo,Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5038195714"],"corresponding_institution_ids":["https://openalex.org/I180203408"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3194844,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/T12676","display_name":"Machine Learning and ELM","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8431078195571899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6892972588539124},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6386154294013977},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6190051436424255},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45739635825157166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2620700001716614},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12871745228767395},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.08315619826316833}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8431078195571899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6892972588539124},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6386154294013977},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6190051436424255},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45739635825157166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2620700001716614},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12871745228767395},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.08315619826316833}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcwkshp64532.2024.11100386","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcwkshp64532.2024.11100386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Globecom Workshops (GC Wkshps)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1538867357","https://openalex.org/W2108598243","https://openalex.org/W2602024037","https://openalex.org/W2605800822","https://openalex.org/W2752796333","https://openalex.org/W3107847925","https://openalex.org/W3134255974","https://openalex.org/W3160403640","https://openalex.org/W4292972809","https://openalex.org/W4315783259","https://openalex.org/W4372341935","https://openalex.org/W6631943919","https://openalex.org/W6640963894","https://openalex.org/W6729956949","https://openalex.org/W6762718338"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W3128807919","https://openalex.org/W3176411177"],"abstract_inverted_index":{"This":[0,149],"paper":[1],"proposes":[2],"a":[3,18,64,68,78,93,125],"method":[4,200],"to":[5,51,81,118,133,141,158,162,189,207],"improve":[6],"the":[7,28,42,45,57,135,146,154,159,172,176,198],"tradeoff":[8],"between":[9],"accuracy":[10,166,217],"and":[11,77,165],"latency":[12,54,99,164,203],"in":[13,31,83,100],"split":[14,32,49,101,111,147,155,182],"inference":[15,33,62,112],"by":[16,35,139,204],"introducing":[17],"vector":[19,23,38,130],"quantization-based":[20],"bottleneck.":[21],"Through":[22],"quantization,":[24],"we":[25,123,178],"significantly":[26,96],"reduce":[27],"traffic":[29],"generated":[30],"and,":[34],"embedding":[36],"multiple":[37],"quantized":[39,131],"bottlenecks":[40,132],"within":[41],"model,":[43],"enable":[44],"selection":[46],"of":[47,153],"optimal":[48],"points":[50,183],"minimize":[52],"total":[53,98,202],"based":[55],"on":[56,145],"available":[58],"communication":[59,160,192,211],"bandwidth.":[60],"Split":[61],"is":[63,92],"technique":[65],"that":[66,128,197],"partitions":[67],"model":[69,126,174],"into":[70],"two":[71],"sections,":[72],"allowing":[73],"an":[74],"IoT":[75],"device":[76],"powerful":[79],"server":[80],"collaborate":[82],"computation,":[84],"potentially":[85],"enhancing":[86],"real-time":[87],"performance.":[88],"Data":[89],"transfer":[90,137,187],"volume":[91,138],"critical":[94],"factor":[95],"influencing":[97],"inference.":[102],"Unlike":[103],"cloud":[104],"inference,":[105],"where":[106],"int-type":[107],"images":[108],"are":[109],"transmitted,":[110],"transfers":[113],"float-type":[114],"intermediate":[115],"representations,":[116],"leading":[117],"substantial":[119],"data":[120,136,186],"transmission.":[121],"Here,":[122],"propose":[124],"architecture":[127],"incorporates":[129],"compress":[134],"50":[140],"200":[142],"times,":[143],"depending":[144],"point.":[148],"enables":[150],"dynamic":[151],"adjustment":[152],"point":[156],"according":[157],"bandwidth":[161],"optimize":[163],"trade-offs.":[167],"In":[168],"our":[169],"experiments,":[170],"using":[171],"EfficientNet-B0":[173],"as":[175],"base,":[177],"identified":[179],"three":[180],"candidate":[181],"with":[184,214],"varying":[185],"volumes":[188],"accommodate":[190],"different":[191,210],"bandwidths.":[193],"The":[194],"results":[195],"show":[196],"proposed":[199],"reduces":[201],"approximately":[205],"5%":[206],"90%":[208],"across":[209],"speed":[212],"environments,":[213],"only":[215],"minimal":[216],"degradation.":[218]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}