{"id":"https://openalex.org/W4399487171","doi":"https://doi.org/10.1145/3649476.3658699","title":"Resource-Aware Saliency-Guided Differentiable Pruning for Deep Neural Networks","display_name":"Resource-Aware Saliency-Guided Differentiable Pruning for Deep Neural Networks","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399487171","doi":"https://doi.org/10.1145/3649476.3658699"},"language":"en","primary_location":{"id":"doi:10.1145/3649476.3658699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","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/A5061729841","display_name":"Uttej Kallakuri","orcid":"https://orcid.org/0009-0004-1150-3903"},"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":true,"raw_author_name":"Uttej Kallakuri","raw_affiliation_strings":["Electrical and Computer Engineering, Johns Hopkins University, USA"],"raw_orcid":"https://orcid.org/0009-0004-1150-3903","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023630054","display_name":"Edward Humes","orcid":"https://orcid.org/0009-0002-3945-0116"},"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":"Edward Humes","raw_affiliation_strings":["Computer Science, University of Maryland, Baltimore County, USA"],"raw_orcid":"https://orcid.org/0009-0002-3945-0116","affiliations":[{"raw_affiliation_string":"Computer Science, University of Maryland, Baltimore County, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"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":["Electrical and Computer Engineering, Johns Hopkins University, USA"],"raw_orcid":"https://orcid.org/0000-0001-5551-2124","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061729841"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":1.1904,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79299316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"694","last_page":"699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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":0.9986000061035156,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9940000176429749,"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/T10320","display_name":"Neural Networks and Applications","score":0.9912999868392944,"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/pruning","display_name":"Pruning","score":0.8307585716247559},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.7749068737030029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7450742721557617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6194778084754944},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5817651748657227},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5816423892974854},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4808012545108795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44065847992897034},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12165477871894836},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1021735668182373}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8307585716247559},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.7749068737030029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450742721557617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6194778084754944},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5817651748657227},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5816423892974854},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4808012545108795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44065847992897034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12165477871894836},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1021735668182373},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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:10.1145/3649476.3658699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","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":13,"referenced_works":["https://openalex.org/W2094756095","https://openalex.org/W2592329255","https://openalex.org/W2604319603","https://openalex.org/W2616014673","https://openalex.org/W2936672709","https://openalex.org/W2945047231","https://openalex.org/W2948818370","https://openalex.org/W2949619037","https://openalex.org/W3184606595","https://openalex.org/W3199014868","https://openalex.org/W3215698464","https://openalex.org/W3215899784","https://openalex.org/W4311007713"],"related_works":["https://openalex.org/W4285277090","https://openalex.org/W4327738859","https://openalex.org/W2348722996","https://openalex.org/W2334570605","https://openalex.org/W3181683615","https://openalex.org/W4286826125","https://openalex.org/W1633485514","https://openalex.org/W1604739066","https://openalex.org/W2115878407","https://openalex.org/W4287323461"],"abstract_inverted_index":{"The":[0,127],"increasing":[1],"demand":[2],"for":[3,124,134,154,175,217,225],"efficient":[4,103],"deep":[5,67],"learning":[6],"model":[7,111,119,184],"deployment":[8],"on":[9,49,91],"Tiny":[10],"Machine":[11],"Learning":[12],"(tinyML)":[13],"and":[14,25,53,60,121,139,219],"Edge":[15],"platforms":[16],"necessitates":[17],"the":[18,77,84,110,116,135,148,166,172,183,203],"development":[19],"of":[20,87,129,137,147,168,192,205],"methods":[21],"that":[22,44],"enable":[23,101],"automated":[24],"effective":[26],"network":[27,69,74],"pruning,":[28],"tailored":[29],"to":[30,58,83,112,114,144,171,186],"tinyML":[31,51,98,125],"hardware":[32,52,195],"constraints.":[33],"In":[34,165],"this":[35],"paper,":[36],"we":[37,100,181],"present":[38],"a":[39,50,66,96,176,209],"novel":[40],"differentiable":[41],"pruning":[42,150],"method":[43],"accepts":[45],"total":[46],"available":[47],"memory":[48],"employs":[54],"saliency":[55],"based":[56],"measurements":[57],"identify":[59],"prune":[61],"less":[62],"significant":[63],"connections":[64],"within":[65,76],"neural":[68],"(DNN).":[70],"Our":[71,106],"approach":[72,131,153,207],"integrates":[73],"compression":[75,136],"training":[78],"process,":[79],"adapting":[80],"resource":[81],"utilization":[82],"specific":[85],"constraints":[86],"FPGAs,":[88],"particularly":[89],"focusing":[90],"on-chip":[92],"memory.":[93],"By":[94],"leveraging":[95],"custom":[97],"accelerator,":[99],"an":[102],"hardware-software":[104],"co-design.":[105],"framework":[107],"further":[108,159],"quantizes":[109],"int-8":[113],"optimize":[115],"balance":[117],"between":[118],"size":[120],"accuracy,":[122],"crucial":[123],"applications.":[126],"efficacy":[128],"our":[130,152,193,206],"is":[132],"examined":[133],"LeNet":[138,161,218],"VGG16":[140],"DNNs.":[141],"When":[142],"compared":[143,170],"similar":[145],"state":[146],"art":[149],"techniques,":[151],"no":[155],"drop":[156,178],"in":[157,179,212],"accuracy":[158,180],"compresses":[160],"by":[162,214,222],"1.15":[163],"\u00d7.":[164,188],"case":[167],"VGG16,":[169],"baseline":[173],"implementation,":[174],"4%":[177],"compress":[182],"up":[185],"55":[187],"A":[189],"comparative":[190],"analysis":[191],"FPGA":[194],"accelerator":[196],"against":[197],"leading":[198],"image":[199],"classification":[200],"accelerators":[201],"emphasizes":[202],"merits":[204],"with":[208],"marked":[210],"improvement":[211],"throughput":[213],"1.46":[215],"\u00d7":[216,224],"energy":[220],"efficiency":[221],"1.7":[223],"VGG16.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}