{"id":"https://openalex.org/W3080183383","doi":"https://doi.org/10.1145/3394486.3403103","title":"AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks","display_name":"AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3080183383","doi":"https://doi.org/10.1145/3394486.3403103","mag":"3080183383"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403103","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/10.1145/3394486.3403103","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006348455","display_name":"Jiancheng Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiancheng Lyu","raw_affiliation_strings":["Qualcomm AI Research, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, San Diego, CA, USA","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328881","display_name":"Shuai Zhang","orcid":"https://orcid.org/0000-0002-4821-6404"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuai Zhang","raw_affiliation_strings":["Qualcomm AI Research, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, San Diego, CA, USA","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101940576","display_name":"Yingyong Qi","orcid":"https://orcid.org/0000-0003-1430-258X"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingyong Qi","raw_affiliation_strings":["Qualcomm AI Research, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, San Diego, CA, USA","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059708262","display_name":"Jack Xin","orcid":"https://orcid.org/0000-0002-6438-8476"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jack Xin","raw_affiliation_strings":["University of California, Irvine, Irvine, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"608","last_page":"616"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9958000183105469,"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/permutation-matrix","display_name":"Permutation matrix","score":0.6785143613815308},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.672736644744873},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.5797979831695557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5736644268035889},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5417760610580444},{"id":"https://openalex.org/keywords/shuffling","display_name":"Shuffling","score":0.5293306112289429},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44560351967811584},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3579685389995575},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34002813696861267},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3038867115974426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23911920189857483}],"concepts":[{"id":"https://openalex.org/C84140500","wikidata":"https://www.wikidata.org/wiki/Q851512","display_name":"Permutation matrix","level":3,"score":0.6785143613815308},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.672736644744873},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.5797979831695557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5736644268035889},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5417760610580444},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.5293306112289429},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44560351967811584},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3579685389995575},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34002813696861267},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3038867115974426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23911920189857483},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C115973184","wikidata":"https://www.wikidata.org/wiki/Q245457","display_name":"Circulant matrix","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394486.3403103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403103","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3394486.3403103","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3394486.3403103","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3394486.3403103","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G165397979","display_name":"Computational and Mathematical Studies of Complexity Reduction Methods for Deep Neural Networks and Applications","funder_award_id":"1854434","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4452921515","display_name":"BIGDATA: Collaborative Research: F: Foundations of Nonconvex Problems in BigData Science and Engineering: Models, Algorithms, and Analysis","funder_award_id":"1632935","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5367883119","display_name":null,"funder_award_id":"DMS-1854434","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5479139866","display_name":null,"funder_award_id":"IIS-1632935","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/W3080183383.pdf","grobid_xml":"https://content.openalex.org/works/W3080183383.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1973396420","https://openalex.org/W1973926472","https://openalex.org/W1990283121","https://openalex.org/W2004886822","https://openalex.org/W2083542343","https://openalex.org/W2089106993","https://openalex.org/W2108598243","https://openalex.org/W2163605009","https://openalex.org/W2166524953","https://openalex.org/W2194197298","https://openalex.org/W2461967896","https://openalex.org/W2778955544","https://openalex.org/W2895478406","https://openalex.org/W2952237618","https://openalex.org/W2963506485","https://openalex.org/W2963519230","https://openalex.org/W2964169985","https://openalex.org/W2964316651","https://openalex.org/W2972442919","https://openalex.org/W3118608800","https://openalex.org/W3121235808","https://openalex.org/W4211027744"],"related_works":["https://openalex.org/W2785357686","https://openalex.org/W4300913961","https://openalex.org/W2963300665","https://openalex.org/W4285790638","https://openalex.org/W2967856490","https://openalex.org/W3013139561","https://openalex.org/W2949607517","https://openalex.org/W4308670488","https://openalex.org/W2917004075","https://openalex.org/W2140809923"],"abstract_inverted_index":{"ShuffleNet":[0],"is":[1,23,31,156],"a":[2,32,35],"state-of-the-art":[3],"light":[4],"weight":[5],"convolutional":[6],"neural":[7,171],"network":[8,52,172],"architecture.":[9],"Its":[10],"basic":[11],"operations":[12],"include":[13],"group,":[14],"channel-wise":[15],"convolution":[16],"and":[17,91,112,169],"channel":[18,21,45],"shuffling.":[19],"However,":[20],"shuffling":[22,30,46],"manually":[24],"designed":[25],"on":[26,107],"empirical":[27],"grounds.":[28],"Mathematically,":[29],"multiplication":[33],"by":[34,47,83],"permutation":[36,49,75,132,150,164],"matrix.":[37],"In":[38,121,184],"this":[39],"paper,":[40],"we":[41,123],"propose":[42],"to":[43,73,100,138,190],"automate":[44],"learning":[48],"matrices":[50,133,136,151],"in":[51,68,94,148,180],"training.":[53],"We":[54,141,160],"introduce":[55],"an":[56],"exact":[57],"Lipschitz":[58],"continuous":[59],"non-convex":[60],"penalty":[61,154,195],"so":[62],"that":[63,126],"it":[64],"can":[65],"be":[66],"incorporated":[67],"the":[69,87,116,127,144,175,185],"stochastic":[70,135],"gradient":[71],"descent":[72],"approximate":[74],"at":[76,86],"high":[77],"precision.":[78],"Exact":[79],"permutations":[80,192],"are":[81,92,178],"obtained":[82],"simple":[84],"rounding":[85],"end":[88],"of":[89,119,131,163],"training":[90],"used":[93],"inference.":[95],"The":[96],"resulting":[97],"network,":[98],"referred":[99],"as":[101],"AutoShuffleNet,":[102],"achieved":[103],"improved":[104],"classification":[105],"accuracies":[106],"data":[108],"from":[109],"CIFAR-10,":[110],"CIFAR-100":[111],"ImageNet":[113],"while":[114],"preserving":[115],"inference":[117],"costs":[118],"ShuffleNet.":[120],"addition,":[122],"found":[124],"experimentally":[125],"standard":[128],"convex":[129,187],"relaxation":[130,188],"into":[134],"leads":[137],"poor":[139],"performance.":[140],"prove":[142],"theoretically":[143],"exactness":[145],"(error":[146],"bounds)":[147],"recovering":[149],"when":[152],"our":[153,194],"function":[155],"zero":[157],"(very":[158],"small).":[159],"present":[161],"examples":[162],"optimization":[165],"through":[166],"graph":[167],"matching":[168],"two-layer":[170],"models":[173],"where":[174],"loss":[176],"functions":[177],"calculated":[179],"closed":[181],"analytical":[182],"form.":[183],"examples,":[186],"failed":[189],"capture":[191],"whereas":[193],"succeeded.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}