{"id":"https://openalex.org/W4221068649","doi":"https://doi.org/10.1109/access.2022.3161622","title":"Resource-Efficient Multi-Task Deep Learning Using a Multi-Path Network","display_name":"Resource-Efficient Multi-Task Deep Learning Using a Multi-Path Network","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4221068649","doi":"https://doi.org/10.1109/access.2022.3161622"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3161622","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3161622","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09740124.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09740124.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100693311","display_name":"Soyeon Park","orcid":"https://orcid.org/0000-0003-1009-8630"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Soyeon Park","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University, Seoul, South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685126","display_name":"Jiho Lee","orcid":"https://orcid.org/0000-0003-2516-1380"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiho Lee","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University, Seoul, South Korea","institution_ids":["https://openalex.org/I67900169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074532898","display_name":"Eunwoo Kim","orcid":"https://orcid.org/0000-0003-0840-0044"},"institutions":[{"id":"https://openalex.org/I67900169","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98","country_code":"KR","type":"education","lineage":["https://openalex.org/I67900169"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eunwoo Kim","raw_affiliation_strings":["School of Computer Science and Engineering, Chung-Ang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Chung-Ang University, Seoul, South Korea","institution_ids":["https://openalex.org/I67900169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100693311"],"corresponding_institution_ids":["https://openalex.org/I67900169"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2776,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60885086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"10","issue":null,"first_page":"32889","last_page":"32899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.996999979019165,"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":0.8657755851745605},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.7545857429504395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6633048057556152},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.617236852645874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6115407943725586},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5934436321258545},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5513908863067627},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5011370182037354},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.476807564496994},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4410291910171509},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41863587498664856},{"id":"https://openalex.org/keywords/instance-based-learning","display_name":"Instance-based learning","score":0.41621583700180054},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3572753369808197},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2235793173313141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657755851745605},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.7545857429504395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6633048057556152},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.617236852645874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6115407943725586},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5934436321258545},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5513908863067627},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5011370182037354},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.476807564496994},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4410291910171509},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41863587498664856},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.41621583700180054},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3572753369808197},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2235793173313141},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3161622","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3161622","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09740124.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c7f208fdb111437387cba1f563c3e980","is_oa":true,"landing_page_url":"https://doaj.org/article/c7f208fdb111437387cba1f563c3e980","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 32889-32899 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3161622","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3161622","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09740124.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1794958148","display_name":null,"funder_award_id":"P0012724,","funder_id":"https://openalex.org/F4320322064","funder_display_name":"Korea Institute for Advancement of Technology"},{"id":"https://openalex.org/G4684601176","display_name":null,"funder_award_id":"SRFC-IT2002-05","funder_id":"https://openalex.org/F4320332195","funder_display_name":"Samsung"},{"id":"https://openalex.org/G4890888927","display_name":null,"funder_award_id":"P0012724","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G5282497172","display_name":null,"funder_award_id":"P0012724","funder_id":"https://openalex.org/F4320322064","funder_display_name":"Korea Institute for Advancement of Technology"},{"id":"https://openalex.org/G889103765","display_name":null,"funder_award_id":"MOTIE","funder_id":"https://openalex.org/F4320322064","funder_display_name":"Korea Institute for Advancement of Technology"},{"id":"https://openalex.org/G992484961","display_name":null,"funder_award_id":"Korea","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320321202","display_name":"Chung-Ang University","ror":"https://ror.org/01r024a98"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322064","display_name":"Korea Institute for Advancement of Technology","ror":"https://ror.org/015w1qa96"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221068649.pdf","grobid_xml":"https://content.openalex.org/works/W4221068649.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W1834627138","https://openalex.org/W1903029394","https://openalex.org/W2102605133","https://openalex.org/W2134797427","https://openalex.org/W2194775991","https://openalex.org/W2307770531","https://openalex.org/W2543539599","https://openalex.org/W2796394093","https://openalex.org/W2798441115","https://openalex.org/W2884886306","https://openalex.org/W2895387432","https://openalex.org/W2943186426","https://openalex.org/W2962860144","https://openalex.org/W2962864421","https://openalex.org/W2963072899","https://openalex.org/W2963430933","https://openalex.org/W2963453233","https://openalex.org/W2963835211","https://openalex.org/W2963854351","https://openalex.org/W2963877604","https://openalex.org/W2964137095","https://openalex.org/W2964247799","https://openalex.org/W2983128379","https://openalex.org/W2984039063","https://openalex.org/W2990138404","https://openalex.org/W3010512657","https://openalex.org/W3034457371","https://openalex.org/W3034867292","https://openalex.org/W3034911677","https://openalex.org/W3041830731","https://openalex.org/W3087406311","https://openalex.org/W3106901158","https://openalex.org/W3108075360","https://openalex.org/W3109135481","https://openalex.org/W3118608800","https://openalex.org/W3128096387","https://openalex.org/W3215245274","https://openalex.org/W4239943352","https://openalex.org/W4385245566","https://openalex.org/W6637551013","https://openalex.org/W6679909955","https://openalex.org/W6730179637","https://openalex.org/W6739901393","https://openalex.org/W6754005058","https://openalex.org/W6766978945","https://openalex.org/W6767140673","https://openalex.org/W6770205404","https://openalex.org/W6771876938","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W3176823731","https://openalex.org/W2914746235","https://openalex.org/W4239943352","https://openalex.org/W2913340405","https://openalex.org/W4307478737","https://openalex.org/W4372260038","https://openalex.org/W2186333919","https://openalex.org/W3021272668","https://openalex.org/W2950678851","https://openalex.org/W2237537322"],"abstract_inverted_index":{"Multi-task":[0],"learning":[1,4,57,81,115,146,163],"(MTL)":[2],"improves":[3],"efficiency":[5],"compared":[6],"to":[7,22,54,63,125,129],"the":[8,18,23,50,61,107,126,132,137],"single-task":[9],"counterpart":[10],"in":[11,89],"that":[12,59],"it":[13,25,36],"performs":[14],"multiple":[15,149],"tasks":[16,65,121,128,150],"at":[17],"same":[19],"time.":[20],"Due":[21],"nature,":[24],"can":[26],"achieve":[27],"generalized":[28],"performance":[29,108,133],"as":[30,32],"well":[31],"alleviate":[33,106],"overfitting.":[34],"However,":[35],"does":[37],"not":[38],"efficiently":[39],"perform":[40],"resource-aware":[41],"inference":[42],"from":[43,110],"a":[44,56,75,79,90,94,100,113,170],"single":[45],"trained":[46],"architecture.":[47],"To":[48,70,105],"address":[49],"issue,":[51],"we":[52,73],"aim":[53],"build":[55],"framework":[58],"minimizes":[60],"cost":[62],"infer":[64],"under":[66],"different":[67],"memory":[68],"budgets.":[69],"this":[71],"end,":[72],"propose":[74],"multi-path":[76,84],"network":[77],"with":[78,99],"self-auxiliary":[80,114,120],"strategy.":[82],"The":[83,119,157],"structure":[85],"contains":[86],"task-specific":[87,123],"paths":[88],"backbone":[91],"network,":[92],"where":[93],"lower-level":[95],"path":[96],"predicts":[97],"earlier":[98,111],"smaller":[101,184],"number":[102],"of":[103,144,172],"parameters.":[104],"degradation":[109],"predictions,":[112],"strategy":[116],"is":[117],"presented.":[118],"convey":[122],"knowledge":[124],"main":[127],"compensate":[130],"for":[131,165],"leak.":[134],"We":[135],"evaluate":[136],"proposed":[138,158],"method":[139,159],"on":[140,177],"an":[141],"extensive":[142],"set":[143],"multi-task":[145,162],"scenarios,":[147],"including":[148],"learning,":[151,153],"hierarchical":[152],"and":[154],"curriculum":[155],"learning.":[156],"outperforms":[160],"existing":[161],"competitors":[164],"most":[166],"scenarios":[167],"about":[168],"by":[169],"margin":[171],"1%":[173],"~":[174,182],"2%":[175],"accuracy":[176],"average":[178],"while":[179],"consuming":[180],"30%":[181],"60%":[183],"computational":[185],"cost.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}