{"id":"https://openalex.org/W3129155488","doi":"https://doi.org/10.1145/3394885.3431628","title":"Dynamic Neural Network to Enable Run-Time Trade-off between Accuracy and Latency","display_name":"Dynamic Neural Network to Enable Run-Time Trade-off between Accuracy and Latency","publication_year":2021,"publication_date":"2021-01-18","ids":{"openalex":"https://openalex.org/W3129155488","doi":"https://doi.org/10.1145/3394885.3431628","mag":"3129155488"},"language":"en","primary_location":{"id":"doi:10.1145/3394885.3431628","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394885.3431628","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394885.3431628","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3394885.3431628","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100419157","display_name":"Li Yang","orcid":"https://orcid.org/0000-0002-2839-6196"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Yang","raw_affiliation_strings":["Arizona State University, Tempe, Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047916979","display_name":"Deliang Fan","orcid":"https://orcid.org/0000-0002-7989-6297"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Deliang Fan","raw_affiliation_strings":["Arizona State University, Tempe, Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":null,"first_page":"587","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.854229748249054},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5189163684844971},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5090922713279724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5047038793563843},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.48015397787094116},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.4555739760398865},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.45457926392555237},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.45456036925315857},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.440138578414917},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4213927686214447},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24252521991729736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24169263243675232},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.239141583442688},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.12109917402267456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.854229748249054},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5189163684844971},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5090922713279724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5047038793563843},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.48015397787094116},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.4555739760398865},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.45457926392555237},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.45456036925315857},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.440138578414917},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4213927686214447},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24252521991729736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24169263243675232},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.239141583442688},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.12109917402267456},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394885.3431628","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394885.3431628","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394885.3431628","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3394885.3431628","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394885.3431628","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394885.3431628","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3325972778","display_name":"Collaborative Research: SaTC: CORE: Small: Understanding and Taming Deterministic Model Bit Flip attacks in Deep Neural Networks","funder_award_id":"2019548","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6833359986","display_name":"CPS: Medium: A Secure, Trustworthy, and Reliable Air Quality Monitoring System for Smart and Connected Communities","funder_award_id":"1931871","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7714242829","display_name":null,"funder_award_id":"2005209;1931871","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8250542359","display_name":"E2CDA: Type II: Non-Volatile In-Memory Processing Unit: Memory, In-Memory Logic and Deep Neural Network","funder_award_id":"2005209","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3129155488.pdf","grobid_xml":"https://content.openalex.org/works/W3129155488.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2524428287","https://openalex.org/W2582745083","https://openalex.org/W2612445135","https://openalex.org/W2796438033","https://openalex.org/W2963000224","https://openalex.org/W2963735024","https://openalex.org/W2963747836","https://openalex.org/W2963766446","https://openalex.org/W2981698279","https://openalex.org/W2982644126","https://openalex.org/W2998470761","https://openalex.org/W3013202691","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W3204400881","https://openalex.org/W3214410901","https://openalex.org/W3204296682","https://openalex.org/W3183118997","https://openalex.org/W2917767146","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044"],"abstract_inverted_index":{"To":[0,148],"deploy":[1],"powerful":[2],"deep":[3],"neural":[4],"network":[5,26,39,55],"(DNN)":[6],"into":[7],"smart,":[8],"but":[9,53],"resource":[10,66,89],"limited":[11,67],"IoT":[12],"devices,":[13],"many":[14],"prior":[15,101],"works":[16,102],"have":[17],"been":[18],"proposed":[19],"to":[20,23,64,76,82,105,111,127,134,187,196],"compress":[21],"DNN":[22,48,115],"reduce":[24,149],"the":[25,74,137,150,185,190,203,207,208,225],"size":[27],"and":[28,91,193,199,219,230,235],"computation":[29],"complexity":[30],"with":[31,211],"negligible":[32],"accuracy":[33,192,229],"degradation,":[34],"such":[35,71],"as":[36,145],"weight":[37],"quantization,":[38],"pruning,":[40],"convolution":[41],"decomposition,":[42],"etc.":[43],"However,":[44,70],"by":[45,116],"utilizing":[46],"conventional":[47],"compression":[49],"methods,":[50],"a":[51,59,85,113,159],"smaller,":[52],"fixed,":[54],"is":[56],"generated":[57],"from":[58],"relative":[60],"large":[61],"background":[62,138],"model":[63,139],"achieve":[65],"hardware":[68,88,197],"acceleration.":[69],"optimization":[72],"lacks":[73],"ability":[75,186],"adjust":[77],"its":[78],"structure":[79],"in":[80,153,169],"real-time":[81],"adapt":[83],"for":[84,140],"dynamic":[86,114,178,209],"computing":[87],"allocation":[90],"workloads.":[92],"In":[93,202],"this":[94,107,154],"paper,":[95],"we":[96,156,205],"mainly":[97],"review":[98],"our":[99],"two":[100],"[13,":[103],"15]":[104],"tackle":[106],"challenge,":[108],"discussing":[109],"how":[110],"construct":[112],"means":[117],"of":[118,181,228],"either":[119],"uniform":[120],"or":[121],"non-uniform":[122],"sub-nets":[123,161,168,213],"generation":[124,162,214],"methods.":[125],"Moreover,":[126],"generate":[128],"multiple":[129,167,182],"nonuniform":[130],"sub-nets,":[131,183],"[15]":[132],"needs":[133],"fully":[135],"retrain":[136],"each":[141],"sub-net":[142],"individually,":[143],"named":[144],"multi-path":[146],"method.":[147],"training":[151,174],"cost,":[152],"work,":[155],"further":[157],"propose":[158],"single-path":[160],"method":[163],"that":[164],"can":[165],"sample":[166],"different":[170,212],"epochs":[171],"within":[172],"one":[173],"round.":[175],"The":[176],"constructed":[177],"DNN,":[179],"consisting":[180],"provides":[184],"run-time":[188,226],"trade-off":[189],"inference":[191],"latency":[194,231],"according":[195],"resources":[198],"environment":[200],"requirements.":[201],"end,":[204],"study":[206],"DNNs":[210],"methods":[215],"on":[216,232],"both":[217,233],"CIFAR-10":[218],"ImageNet":[220],"dataset.":[221],"We":[222],"also":[223],"present":[224],"tuning":[227],"GPU":[234],"CPU.":[236]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}