{"id":"https://openalex.org/W3163244872","doi":"https://doi.org/10.1109/icpr48806.2021.9413182","title":"Activation Density Driven Efficient Pruning in Training","display_name":"Activation Density Driven Efficient Pruning in Training","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3163244872","doi":"https://doi.org/10.1109/icpr48806.2021.9413182","mag":"3163244872"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9413182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5059671888","display_name":"Timothy Foldy-Porto","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy Foldy-Porto","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079036687","display_name":"Yeshwanth Venkatesha","orcid":null},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yeshwanth Venkatesha","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050310538","display_name":"Priyadarshini Panda","orcid":"https://orcid.org/0000-0002-4167-6782"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priyadarshini Panda","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":0.4774,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71178537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"8929","last_page":"8936"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9955999851226807,"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":0.8923640847206116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527014017105103},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.7218113541603088},{"id":"https://openalex.org/keywords/network-architecture","display_name":"Network architecture","score":0.5153748393058777},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5042232275009155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48574620485305786},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.47819140553474426},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4586517810821533},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4506809413433075},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.44005656242370605},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3223220407962799},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18170961737632751}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.8923640847206116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527014017105103},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.7218113541603088},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.5153748393058777},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5042232275009155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48574620485305786},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.47819140553474426},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4586517810821533},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4506809413433075},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.44005656242370605},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3223220407962799},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18170961737632751},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr48806.2021.9413182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9413182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3974418817","display_name":"CRII: SHF: Efficiency-Aware Robust Implementation of Neural Networks with Algorithm-Hardware Co-design","funder_award_id":"1947826","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":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1686810756","https://openalex.org/W2114766824","https://openalex.org/W2119144962","https://openalex.org/W2167215970","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2513419314","https://openalex.org/W2520760693","https://openalex.org/W2554302513","https://openalex.org/W2565851976","https://openalex.org/W2585720638","https://openalex.org/W2614143469","https://openalex.org/W2625457103","https://openalex.org/W2798544842","https://openalex.org/W2805003733","https://openalex.org/W2894740066","https://openalex.org/W2896409484","https://openalex.org/W2904473220","https://openalex.org/W2948635472","https://openalex.org/W2950248853","https://openalex.org/W2951569836","https://openalex.org/W2962851801","https://openalex.org/W2963000224","https://openalex.org/W2963247446","https://openalex.org/W2963674932","https://openalex.org/W2963813662","https://openalex.org/W2964261616","https://openalex.org/W3091661482","https://openalex.org/W3118608800","https://openalex.org/W4236868170","https://openalex.org/W4240168186","https://openalex.org/W6637242042","https://openalex.org/W6677103964","https://openalex.org/W6684563725","https://openalex.org/W6726973340","https://openalex.org/W6730146958","https://openalex.org/W6754807246","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2081982437","https://openalex.org/W4394857231","https://openalex.org/W2027050655","https://openalex.org/W3028244590","https://openalex.org/W4254349500","https://openalex.org/W2014369232","https://openalex.org/W3122042562","https://openalex.org/W2050078012","https://openalex.org/W2060761133","https://openalex.org/W4205470293"],"abstract_inverted_index":{"Neural":[0],"network":[1,58,154,206],"pruning":[2,22,40,53,172],"with":[3,9,16,144,181],"suitable":[4],"retraining":[5,42],"can":[6],"yield":[7],"networks":[8,28,123,177],"considerably":[10],"fewer":[11],"parameters":[12,130],"than":[13,167],"the":[14,46,63,82,92,141,148,153],"original":[15,47],"comparable":[17,146],"degrees":[18],"of":[19,91,108,169],"accuracy.":[20,48],"Typical":[21],"methods":[23],"require":[24],"large,":[25],"fully":[26],"trained":[27,207],"as":[29,201],"a":[30,37,51,57,105,204],"starting":[31],"point":[32],"from":[33,209],"which":[34],"they":[35],"perform":[36],"time-intensive":[38],"iterative":[39],"and":[41,112,117,131],"procedure":[43],"to":[44,67,80,101,125,147,194,203],"regain":[45],"We":[49,73],"propose":[50],"novel":[52],"method":[54,95,184],"that":[55,164],"prunes":[56],"real-time":[59],"during":[60,157],"training,":[61,158],"reducing":[62,152],"overall":[64],"training":[65,162,175,189],"time":[66],"achieve":[68,160],"an":[69,75],"efficient":[70],"compressed":[71,176],"network.":[72,93,150],"introduce":[74],"activation":[76],"density":[77],"based":[78],"analysis":[79],"identify":[81],"optimal":[83],"relative":[84],"sizing":[85],"or":[86],"compression":[87],"for":[88],"each":[89],"layer":[90],"Our":[94],"is":[96],"architecture":[97],"agnostic,":[98],"allowing":[99],"it":[100],"be":[102],"employed":[103],"on":[104,114],"wide":[106],"variety":[107],"systems.":[109],"For":[110],"VGG-19":[111],"ResNet18":[113],"CIFAR-10,":[115],"CIFAR-100,":[116],"TinyImageNet,":[118],"we":[119,159],"obtain":[120],"exceedingly":[121],"sparse":[122],"(up":[124],"200":[126],"x":[127,134,193,196],"reduction":[128,135,187],"in":[129,136,140,188],"over":[132],"60":[133],"inference":[137],"compute":[138,190],"operations":[139],"best":[142],"case)":[143],"accuracy":[145],"baseline":[149,205],"By":[151],"size":[155],"periodically":[156],"total":[161],"times":[163],"are":[165],"shorter":[166],"those":[168],"previously":[170],"proposed":[171,183],"methods.":[173],"Furthermore,":[174],"at":[178,198],"different":[179],"epochs":[180],"our":[182],"yields":[185],"considerable":[186],"complexity":[191],"(1.6":[192],"3.2":[195],"lower)":[197],"near":[199],"iso-accuracy":[200],"compared":[202],"entirely":[208],"scratch.":[210]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}