{"id":"https://openalex.org/W4386546945","doi":"https://doi.org/10.1145/3623380","title":"Reg-Tune: A Regression-Focused Fine-Tuning Approach for Profiling Low Energy Consumption and Latency","display_name":"Reg-Tune: A Regression-Focused Fine-Tuning Approach for Profiling Low Energy Consumption and Latency","publication_year":2023,"publication_date":"2023-09-08","ids":{"openalex":"https://openalex.org/W4386546945","doi":"https://doi.org/10.1145/3623380"},"language":"en","primary_location":{"id":"doi:10.1145/3623380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623380","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623380","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3623380","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007957361","display_name":"Arnab Neelim Mazumder","orcid":"https://orcid.org/0000-0002-9550-7917"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Arnab Neelim Mazumder","raw_affiliation_strings":["University of Maryland Baltimore County, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0002-9550-7917","affiliations":[{"raw_affiliation_string":"University of Maryland Baltimore County, Baltimore, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023316624","display_name":"Farshad Safavi","orcid":"https://orcid.org/0000-0002-6905-0781"},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farshad Safavi","raw_affiliation_strings":["University of Maryland Baltimore County, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0002-6905-0781","affiliations":[{"raw_affiliation_string":"University of Maryland Baltimore County, Baltimore, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010792548","display_name":"Maryam Rahnemoonfar","orcid":"https://orcid.org/0000-0001-9358-2836"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Rahnemoonfar","raw_affiliation_strings":["Lehigh University, Bethlehem, USA"],"raw_orcid":"https://orcid.org/0000-0001-9358-2836","affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084010501","display_name":"Tinoosh Mohsenin","orcid":"https://orcid.org/0000-0001-5551-2124"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tinoosh Mohsenin","raw_affiliation_strings":["Johns Hopkins University, Baltimore, USA"],"raw_orcid":"https://orcid.org/0000-0001-5551-2124","affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5007957361"],"corresponding_institution_ids":["https://openalex.org/I79272384"],"apc_list":null,"apc_paid":null,"fwci":0.5692,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.68413781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"23","issue":"3","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9965000152587891,"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"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9944999814033508,"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":0.791691780090332},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6553224325180054},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6436440944671631},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6258448362350464},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6038334965705872},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5371724963188171},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5191754102706909},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5135765075683594},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4487546384334564},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.44564756751060486},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4255313277244568},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4148794114589691},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.306438684463501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2503458857536316},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0949939489364624},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09118300676345825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791691780090332},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6553224325180054},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6436440944671631},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6258448362350464},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6038334965705872},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5371724963188171},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5191754102706909},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5135765075683594},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4487546384334564},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.44564756751060486},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4255313277244568},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4148794114589691},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.306438684463501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2503458857536316},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0949939489364624},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09118300676345825},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3623380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623380","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623380","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3623380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623380","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623380","source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3634866725","display_name":null,"funder_award_id":"W911NF2120076","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386546945.pdf","grobid_xml":"https://content.openalex.org/works/W4386546945.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W123295786","https://openalex.org/W1901129140","https://openalex.org/W2026297770","https://openalex.org/W2289252105","https://openalex.org/W2559655401","https://openalex.org/W2612445135","https://openalex.org/W2762597430","https://openalex.org/W2792923869","https://openalex.org/W2795256832","https://openalex.org/W2884780389","https://openalex.org/W2917008732","https://openalex.org/W2953554277","https://openalex.org/W2963122961","https://openalex.org/W2963163009","https://openalex.org/W2963526839","https://openalex.org/W2963918968","https://openalex.org/W2964081807","https://openalex.org/W2974514820","https://openalex.org/W2988454569","https://openalex.org/W3006336861","https://openalex.org/W3008746569","https://openalex.org/W3092256386","https://openalex.org/W3122795696","https://openalex.org/W3147050786","https://openalex.org/W3162524694","https://openalex.org/W3175205795","https://openalex.org/W3175548485","https://openalex.org/W3177366646","https://openalex.org/W3199014868","https://openalex.org/W3200687135","https://openalex.org/W3211902324","https://openalex.org/W3215698464","https://openalex.org/W3215899784","https://openalex.org/W4226209055","https://openalex.org/W4242577057","https://openalex.org/W4285186252","https://openalex.org/W4295308832","https://openalex.org/W4295855343","https://openalex.org/W4297775537","https://openalex.org/W4306794854","https://openalex.org/W4308828462","https://openalex.org/W4313009049","https://openalex.org/W4367848206","https://openalex.org/W4381715422","https://openalex.org/W4385187267","https://openalex.org/W4388118262"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2074043759","https://openalex.org/W3042736233","https://openalex.org/W2082487009","https://openalex.org/W2373535795","https://openalex.org/W2406926880","https://openalex.org/W4237139544","https://openalex.org/W2787763930"],"abstract_inverted_index":{"Fine-tuning":[0],"deep":[1,32],"neural":[2,33,101],"networks":[3,34,102],"is":[4,177],"pivotal":[5],"for":[6,145,171,205,221,239,262,271,292,303],"creating":[7],"inference":[8],"modules":[9],"that":[10],"can":[11,60],"be":[12,61],"suitably":[13],"imported":[14],"to":[15,50,87,97,120,139,158,163,217,231,289,313],"edge":[16,109,310],"or":[17,131,236],"field-programmable":[18],"gate":[19],"array":[20],"(FPGA)":[21],"platforms.":[22,74,253],"Traditionally,":[23],"exploration":[24],"of":[25,31,54,92,100,117,123,180,247,306],"different":[26,72,93,121,250,264],"parameters":[27],"throughout":[28],"the":[29,51,57,90,141,155,166,174,181,209,219,224,233,240,244,259],"layers":[30],"has":[35],"been":[36],"done":[37],"using":[38],"grid":[39],"search":[40,58],"and":[41,65,108,187,193,196,215,267,273,298],"other":[42],"brute":[43],"force":[44],"techniques.":[45],"Although":[46],"these":[47,152,191],"methods":[48],"lead":[49],"optimal":[52],"choice":[53],"network":[55],"parameters,":[56],"process":[59,261],"very":[62],"time":[63],"consuming":[64],"may":[66],"not":[67],"consider":[68],"deployment":[69,99,172],"constraints":[70],"across":[71,249,268],"target":[73,156,175,225],"This":[75],"work":[76],"addresses":[77],"this":[78,255],"problem":[79],"by":[80,113],"proposing":[81],"Reg-Tune,":[82],"a":[83,115,178],"regression-based":[84],"profiling":[85,260],"approach":[86,277],"quickly":[88],"determine":[89],"trend":[91,220],"metrics":[94],"in":[95,279,301],"relation":[96],"hardware":[98],"on":[103,154,173,223,296,309],"tinyML":[104,251],"platforms":[105,270],"like":[106],"FPGAs":[107],"devices.":[110],"We":[111],"start":[112],"training":[114],"handful":[116],"configurations":[118,153,195],"belonging":[119],"combinations":[122],"\\(\\mathcal":[124,132],"{NN}\\scriptstyle":[125,133],"\\langle":[126,134],"q":[127,183,211],"(quantization),\\,s":[128],"(scaling)\\rangle":[129],"\\displaystyle\\)":[130,137],"r":[135,185,213],"(resolution),\\,s\\rangle":[136],"workloads":[138],"generate":[140,159],"accuracy":[142,242],"values":[143],"respectively":[144],"their":[146,197],"corresponding":[147],"application.":[148],"Next,":[149],"we":[150,257],"deploy":[151],"device":[157,176,252],"energy/latency":[160,248],"values.":[161],"According":[162],"our":[164],"hypothesis,":[165],"most":[167],"energy-efficient":[168],"configuration":[169,238],"suitable":[170],"function":[179],"variables":[182,210],",":[184,186,212,214],"s":[188,216],".":[189],"Finally,":[190],"trained":[192],"deployed":[194],"related":[198],"results":[199,278],"are":[200],"used":[201],"as":[202],"data":[203],"points":[204],"polynomial":[206],"regression":[207],"with":[208],"realize":[218],"accuracy/energy/latency":[222],"device.":[226],"Our":[227,276],"setup":[228],"allows":[229],"us":[230],"choose":[232],"near-optimal":[234],"energy-consuming":[235],"latency-driven":[237],"desired":[241],"from":[243],"contour":[245],"profiles":[246],"To":[254],"extent,":[256],"demonstrate":[258],"three":[263],"case":[265],"studies":[266],"two":[269],"energy":[272,285],"latency":[274,302],"fine-tuning.":[275],"at":[280],"least":[281],"5.7":[282],"\\(\\times\\)":[283],"better":[284],"efficiency":[286],"when":[287],"compared":[288,312],"recent":[290],"implementations":[291],"human":[293],"activity":[294],"recognition":[295],"FPGA":[297],"74.6%":[299],"reduction":[300],"semantic":[304],"segmentation":[305],"aerial":[307],"imagery":[308],"devices":[311],"baseline":[314],"deployments.":[315]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}