{"id":"https://openalex.org/W3036239992","doi":"https://doi.org/10.23919/date48585.2020.9116416","title":"AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency","display_name":"AntiDote: Attention-based Dynamic Optimization for Neural Network Runtime Efficiency","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3036239992","doi":"https://doi.org/10.23919/date48585.2020.9116416","mag":"3036239992"},"language":"en","primary_location":{"id":"doi:10.23919/date48585.2020.9116416","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5103085687","display_name":"Fuxun Yu","orcid":"https://orcid.org/0000-0002-4880-6658"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fuxun Yu","raw_affiliation_strings":["George Mason University, Fairfax, VA, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100767202","display_name":"Chenchen Liu","orcid":"https://orcid.org/0000-0001-7749-0640"},"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":"Chenchen Liu","raw_affiliation_strings":["University of Maryland, Baltimore County, Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401427","display_name":"Di Wang","orcid":"https://orcid.org/0000-0002-3911-8159"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["Microsoft, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651384","display_name":"Yanzhi Wang","orcid":"https://orcid.org/0000-0002-3024-7990"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhi Wang","raw_affiliation_strings":["Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441957","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0003-2790-976X"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["George Mason University, Fairfax, VA, USA"],"affiliations":[{"raw_affiliation_string":"George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103085687"],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.3908,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61006923,"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":"951","last_page":"956"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9972000122070312,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9958999752998352,"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":0.7392167448997498},{"id":"https://openalex.org/keywords/antidote","display_name":"Antidote","score":0.6665202975273132},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6221468448638916},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39559513330459595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3502570688724518},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07068562507629395}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392167448997498},{"id":"https://openalex.org/C2779365888","wikidata":"https://www.wikidata.org/wiki/Q194168","display_name":"Antidote","level":3,"score":0.6665202975273132},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6221468448638916},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39559513330459595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3502570688724518},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07068562507629395},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C29730261","wikidata":"https://www.wikidata.org/wiki/Q274160","display_name":"Toxicity","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date48585.2020.9116416","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date48585.2020.9116416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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":39,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2108598243","https://openalex.org/W2143612262","https://openalex.org/W2518108298","https://openalex.org/W2553910756","https://openalex.org/W2613718673","https://openalex.org/W2752037867","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2896006880","https://openalex.org/W2896457183","https://openalex.org/W2900423325","https://openalex.org/W2928560789","https://openalex.org/W2955856103","https://openalex.org/W2962965870","https://openalex.org/W2963000224","https://openalex.org/W2963263347","https://openalex.org/W2963341956","https://openalex.org/W2963363373","https://openalex.org/W2963403868","https://openalex.org/W2963420686","https://openalex.org/W2963674932","https://openalex.org/W2972626605","https://openalex.org/W3013407975","https://openalex.org/W3020967014","https://openalex.org/W4385245566","https://openalex.org/W6620707391","https://openalex.org/W6725543821","https://openalex.org/W6726275242","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6743912273","https://openalex.org/W6753412334","https://openalex.org/W6755207826","https://openalex.org/W6755526309","https://openalex.org/W6755904014","https://openalex.org/W6765319836","https://openalex.org/W6767164273","https://openalex.org/W6768372512"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2350692079","https://openalex.org/W3160708701","https://openalex.org/W2568088706","https://openalex.org/W1975506238","https://openalex.org/W2529508190","https://openalex.org/W2409552309","https://openalex.org/W1970537717","https://openalex.org/W3127792877"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"achieved":[4],"great":[5],"cognitive":[6],"performance":[7],"at":[8],"the":[9,17,27,68,77,98,150,159,168,176,182],"expense":[10],"of":[11,209],"considerable":[12],"computation":[13,18],"load.":[14],"To":[15],"relieve":[16],"load,":[19],"many":[20],"optimization":[21,91,108,124,131],"works":[22,46],"are":[23],"developed":[24],"to":[25,167],"reduce":[26],"model":[28,35,49,69,183],"redundancy":[29,147,162],"by":[30,125],"identifying":[31],"and":[32,41,75,114,142,179],"removing":[33],"insignificant":[34],"components,":[36],"such":[37],"as":[38,119,121],"weight":[39],"sparsity":[40],"filter":[42],"pruning.":[43],"However,":[44],"these":[45],"only":[47,81],"evaluate":[48],"components\u2019":[50],"static":[51,78],"significance":[52,71],"with":[53,61,148,186,203],"internal":[54],"parameter":[55],"information,":[56],"ignoring":[57],"their":[58],"dynamic":[59,89,107,130,177],"interaction":[60],"external":[62],"inputs.":[63],"With":[64],"per-input":[65,145],"feature":[66,116,146,160,189],"activation,":[67],"component":[70],"can":[72,80,139,156],"dynamically":[73],"change,":[74],"thus":[76],"methods":[79],"achieve":[82],"sub-optimal":[83],"results.":[84],"Therefore,":[85],"we":[86,103],"propose":[87,104],"a":[88,105,129],"CNN":[90],"framework":[92,109,132],"in":[93,163],"this":[94],"work.":[95],"Based":[96],"on":[97,207],"neural":[99],"network":[100],"attention":[101],"mechanism,":[102],"comprehensive":[106],"including":[110],"(1)":[111,136],"testing-phase":[112],"channel":[113],"column":[115],"map":[117,161],"pruning,":[118],"well":[120],"(2)":[122,153],"training-phase":[123],"targeted":[126],"dropout.":[127],"Such":[128],"has":[133],"several":[134],"benefits:":[135],"First,":[137],"it":[138,155],"accurately":[140],"identify":[141],"aggressively":[143],"remove":[144,158],"considering":[149],"model-input":[151],"interaction;":[152],"Meanwhile,":[154],"maximally":[157],"various":[164,208],"dimensions":[165],"thanks":[166],"multi-dimension":[169],"flexibility;":[170],"(3)":[171],"The":[172],"training-testing":[173],"co-optimization":[174],"favors":[175],"pruning":[178,190],"helps":[180],"maintain":[181],"accuracy":[184,205],"even":[185],"very":[187],"high":[188],"ratio.":[191],"Extensive":[192],"experiments":[193],"show":[194],"that":[195],"our":[196],"method":[197],"could":[198],"bring":[199],"37.4%\u223c54.5%":[200],"FLOPs":[201],"reduction":[202],"negligible":[204],"drop":[206],"test":[210],"networks.":[211]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}