{"id":"https://openalex.org/W2034520351","doi":"https://doi.org/10.1145/2623330.2623618","title":"Supervised deep learning with auxiliary networks","display_name":"Supervised deep learning with auxiliary networks","publication_year":2014,"publication_date":"2014-08-22","ids":{"openalex":"https://openalex.org/W2034520351","doi":"https://doi.org/10.1145/2623330.2623618","mag":"2034520351"},"language":"en","primary_location":{"id":"doi:10.1145/2623330.2623618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Southwest Jiaotong University, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106943333","display_name":"Guangjian Tian","orcid":"https://orcid.org/0009-0004-5377-2730"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangjian Tian","raw_affiliation_strings":["Huawei Noah's Ark Lab, Hong Kong, Hong Kong","HUAWEI Noah's Ark LAB, Hong Kong, Hong Kong#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"HUAWEI Noah's Ark LAB, Hong Kong, Hong Kong#TAB#","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028877572","display_name":"Yadong Mu","orcid":"https://orcid.org/0000-0001-7815-3750"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Mu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Hong Kong, Hong Kong","HUAWEI Noah's Ark LAB, Hong Kong, Hong Kong#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"HUAWEI Noah's Ark LAB, Hong Kong, Hong Kong#TAB#","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380499","display_name":"Wei Fan","orcid":"https://orcid.org/0000-0002-0342-6272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Fan","raw_affiliation_strings":["david.fanwei, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"david.fanwei, Hong Kong, Hong Kong","institution_ids":[]}]}],"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":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"361"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9997000098228455,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7642532587051392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7431944012641907},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.7074544429779053},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.654399037361145},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6481151580810547},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6079516410827637},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6067599058151245},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5719473361968994},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5536834597587585},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4470349848270416},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.43865767121315},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4383723735809326},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4277942180633545},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42144763469696045},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4180719554424286},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3490203619003296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642532587051392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7431944012641907},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7074544429779053},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.654399037361145},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6481151580810547},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6079516410827637},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6067599058151245},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5719473361968994},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5536834597587585},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4470349848270416},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.43865767121315},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4383723735809326},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4277942180633545},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42144763469696045},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4180719554424286},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3490203619003296},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2623330.2623618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2623330.2623618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1434027941","display_name":null,"funder_award_id":"2014CB340304","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W16016350","https://openalex.org/W71795751","https://openalex.org/W1498436455","https://openalex.org/W1533861849","https://openalex.org/W1613249581","https://openalex.org/W1987848744","https://openalex.org/W1994197834","https://openalex.org/W2025768430","https://openalex.org/W2038276547","https://openalex.org/W2044195942","https://openalex.org/W2072128103","https://openalex.org/W2086953401","https://openalex.org/W2100495367","https://openalex.org/W2104208555","https://openalex.org/W2110798204","https://openalex.org/W2112796928","https://openalex.org/W2118858186","https://openalex.org/W2135217348","https://openalex.org/W2135306627","https://openalex.org/W2136922672","https://openalex.org/W2138857742","https://openalex.org/W2145094598","https://openalex.org/W2146672645","https://openalex.org/W2149824585","https://openalex.org/W2152175008","https://openalex.org/W2157364932","https://openalex.org/W2162262658","https://openalex.org/W2163605009","https://openalex.org/W2168013545","https://openalex.org/W2218318129","https://openalex.org/W2293597654","https://openalex.org/W2596585349","https://openalex.org/W2604272474","https://openalex.org/W2606321545","https://openalex.org/W2914484425","https://openalex.org/W2990138404","https://openalex.org/W2997183031","https://openalex.org/W2997574889","https://openalex.org/W4231109964","https://openalex.org/W4238404964","https://openalex.org/W4299828299"],"related_works":["https://openalex.org/W2618574054","https://openalex.org/W2911822711","https://openalex.org/W4385524141","https://openalex.org/W3018979822","https://openalex.org/W3026616975","https://openalex.org/W4288018014","https://openalex.org/W4297776111","https://openalex.org/W2989784533","https://openalex.org/W2996058201","https://openalex.org/W3174759195"],"abstract_inverted_index":{"Deep":[0],"learning":[1,7,67,158],"well":[2],"demonstrates":[3,228],"its":[4],"potential":[5],"in":[6],"latent":[8],"feature":[9],"representations.":[10],"Recent":[11],"years":[12],"have":[13,44],"witnessed":[14],"an":[15],"increasing":[16],"enthusiasm":[17],"for":[18,48,154],"regularizing":[19],"deep":[20,66,201,245],"neural":[21],"networks":[22,173,202],"by":[23,81,181,236],"incorporating":[24],"various":[25],"side":[26,97],"information,":[27],"such":[28,42],"as":[29,146],"user-provided":[30],"labels":[31],"or":[32,84,135],"pairwise":[33],"constraints.":[34],"However,":[35],"the":[36,60,78,105,117,143,156,160,183,190,212,234,238,253,259,272],"effectiveness":[37],"and":[38,102,120,163,179,203,211,224,244],"parameter":[39,157],"sensitivity":[40],"of":[41,56,62,96,107,130,159,185,215],"algorithms":[43],"been":[45],"major":[46,54],"obstacles":[47],"putting":[49],"them":[50],"into":[51],"practice.":[52],"The":[53,171,218],"contribution":[55],"our":[57,113],"work":[58],"is":[59,99,151,255],"exposition":[61],"a":[63],"novel":[64],"supervised":[65,204],"algorithm,":[68],"which":[69,131],"distinguishes":[70],"from":[71],"two":[72,126,172],"unique":[73],"traits.":[74],"First,":[75],"it":[76,150],"regularizes":[77],"network":[79,145],"construction":[80],"utilizing":[82],"similarity":[83],"dissimilarity":[85],"constraints":[86],"between":[87],"data":[88,122,137],"pairs,":[89],"rather":[90],"than":[91],"sample-specific":[92],"annotations.":[93],"Such":[94],"kind":[95],"information":[98,119],"more":[100],"flexible":[101,213],"greatly":[103],"mitigates":[104],"workload":[106],"annotators.":[108],"Secondly,":[109],"unlike":[110],"prior":[111,197],"works,":[112],"proposed":[114,191],"algorithm":[115,192],"decouples":[116],"supervision":[118,134,216],"intrinsic":[121],"structure.":[123],"We":[124,188],"design":[125],"heterogeneous":[127],"networks,":[128,240],"each":[129,177],"encodes":[132],"either":[133],"unsupervised":[136,200],"structure":[138],"respectively.":[139],"Specifically,":[140],"we":[141],"term":[142],"supervision-oriented":[144],"\"auxiliary":[147],"network\"":[148],"since":[149],"principally":[152],"used":[153],"facilitating":[155],"other":[161,178],"one":[162],"will":[164],"be":[165],"removed":[166],"when":[167,248],"handling":[168],"out-of-sample":[169],"data.":[170],"are":[174,251],"complementary":[175],"to":[176,265,271],"bridged":[180],"enforcing":[182],"correlation":[184],"their":[186],"parameters.":[187],"name":[189],"SUpervision-Guided":[193],"AutoencodeR":[194],"(SUGAR).":[195],"Comparing":[196],"works":[198],"on":[199,221,241],"learning,":[205],"SUGAR":[206,230],"better":[207],"balances":[208],"numerical":[209],"tractability":[210],"utilization":[214],"information.":[217],"classification":[219],"performance":[220,235,254],"MNIST":[222],"digits":[223],"eight":[225],"benchmark":[226],"datasets":[227],"that":[229],"can":[231],"effectively":[232],"improve":[233],"using":[237],"auxiliary":[239],"both":[242],"shallow":[243],"architectures.":[246],"Particularly,":[247],"multiple":[249],"SUGARs":[250],"stacked,":[252],"significantly":[256],"boosted.":[257],"On":[258],"selected":[260],"benchmarks,":[261],"ours":[262],"achieve":[263],"up":[264],"11.35%":[266],"relative":[267],"accuracy":[268],"improvement":[269],"compared":[270],"state-of-the-art":[273],"models.":[274]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}