{"id":"https://openalex.org/W3090337104","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207329","title":"A Novel DNN Training Framework via Data Sampling and Multi-Task Optimization","display_name":"A Novel DNN Training Framework via Data Sampling and Multi-Task Optimization","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090337104","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207329","mag":"3090337104"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5100714035","display_name":"Boyu Zhang","orcid":"https://orcid.org/0000-0001-8012-9311"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Boyu Zhang","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006614329","display_name":"A. K. Qin","orcid":"https://orcid.org/0000-0001-6631-1651"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"A. K. Qin","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083939413","display_name":"Hong Pan","orcid":"https://orcid.org/0000-0002-0539-7997"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hong Pan","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020449921","display_name":"Timos Sellis","orcid":"https://orcid.org/0000-0002-9067-5639"},"institutions":[{"id":"https://openalex.org/I57093077","display_name":"Swinburne University of Technology","ror":"https://ror.org/031rekg67","country_code":"AU","type":"education","lineage":["https://openalex.org/I57093077"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Timos Sellis","raw_affiliation_strings":["Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Software Engineering, Swinburne University of Technology, Melbourne, Australia","institution_ids":["https://openalex.org/I57093077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I57093077"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"269","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T12676","display_name":"Machine Learning and ELM","score":0.9993000030517578,"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":0.7684828639030457},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7675511837005615},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6789900064468384},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6749775409698486},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6629509925842285},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6619076728820801},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6591736078262329},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6212162375450134},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5380486845970154},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5307607054710388},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.5017120838165283},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4792190194129944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0910407304763794},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07300141453742981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7684828639030457},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7675511837005615},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6789900064468384},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6749775409698486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6629509925842285},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6619076728820801},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6591736078262329},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6212162375450134},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5380486845970154},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5307607054710388},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.5017120838165283},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4792190194129944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0910407304763794},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07300141453742981},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:researchbank.swinburne.edu.au:05b4b966-cbfc-41af-9da0-f39ca7d1ae94/1","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.3/458399","pdf_url":null,"source":{"id":"https://openalex.org/S4306401157","display_name":"Swinburne Research Bank (Swinburne University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I57093077","host_organization_name":"Swinburne University of Technology","host_organization_lineage":["https://openalex.org/I57093077"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, United Kingdom, 19-24 July 2020, 9207329","raw_type":null},{"id":"pmh:oai:researchbank.swinburne.edu.au:9169ffe2-e194-42d9-bccb-b107beb0f515/1","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.3/456379","pdf_url":null,"source":{"id":"https://openalex.org/S4306401157","display_name":"Swinburne Research Bank (Swinburne University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I57093077","host_organization_name":"Swinburne University of Technology","host_organization_lineage":["https://openalex.org/I57093077"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Computational Intelligence Society (IEEE WCCI 2020): International Joint Conference on Neural Networks (IJCNN 2020), 19 - 24th July, 2020, Glasgow (UK)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W76331760","https://openalex.org/W122178443","https://openalex.org/W1416942850","https://openalex.org/W1533026269","https://openalex.org/W1582774210","https://openalex.org/W1821462560","https://openalex.org/W1958291604","https://openalex.org/W1977295328","https://openalex.org/W1980038761","https://openalex.org/W1981552604","https://openalex.org/W2016043834","https://openalex.org/W2058399474","https://openalex.org/W2066671570","https://openalex.org/W2102017903","https://openalex.org/W2108598243","https://openalex.org/W2113145584","https://openalex.org/W2165698076","https://openalex.org/W2178768799","https://openalex.org/W2279098554","https://openalex.org/W2413527939","https://openalex.org/W2727592975","https://openalex.org/W2770298516","https://openalex.org/W2810440851","https://openalex.org/W2883262743","https://openalex.org/W2885854619","https://openalex.org/W2914746235","https://openalex.org/W2963163009","https://openalex.org/W2963250052","https://openalex.org/W2963446712","https://openalex.org/W2963703618","https://openalex.org/W2963787134","https://openalex.org/W2969945254","https://openalex.org/W3104887532","https://openalex.org/W4239943352","https://openalex.org/W4254751698","https://openalex.org/W4394662461","https://openalex.org/W6603190504","https://openalex.org/W6605098596","https://openalex.org/W6638523607","https://openalex.org/W6676544178","https://openalex.org/W6685777725","https://openalex.org/W6743446608","https://openalex.org/W6752378494","https://openalex.org/W6752922119","https://openalex.org/W6766816269","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W2551249631","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W1999699871","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W1972167985","https://openalex.org/W2971899271","https://openalex.org/W2350644419"],"abstract_inverted_index":{"Conventional":[0],"DNN":[1,99,133,155,285],"training":[2,8,28,35,40,60,72,97,123,134,141,148,178,186,232,238,258,263,306],"paradigms":[3],"typically":[4],"rely":[5],"on":[6,162,248,255,273,289],"one":[7,11,176,256],"set":[9,36,46,77,149],"and":[10,117,142,197,277],"validation":[12,45,76,143,214],"set,":[13,29],"obtained":[14,174],"by":[15,234],"partitioning":[16],"an":[17,81],"annotated":[18],"dataset":[19],"available":[20],"for":[21,39],"the":[22,41,44,51,55,59,75,85,93,121,146,167,199,208,213,236,267,271,297,300,304],"purpose":[23],"of":[24,54,84,140,157,293,299],"training,":[25],"namely":[26],"gross":[27,147],"in":[30,70,224],"a":[31,98,103,131,154,158,192,274],"certain":[32],"way.":[33],"The":[34,219],"is":[37,47,108],"used":[38,48,284],"model":[42,57,156,177,185,237,257,262],"while":[43,165],"to":[49,62,89,101,110,120,180,183,240,280],"estimate":[50,83],"generalization":[52,86,249],"performance":[53,87,211,250],"trained":[56,204],"as":[58],"proceeds":[61],"avoid":[63],"over-fitting.":[64],"There":[65],"exist":[66],"two":[67],"major":[68],"issues":[69],"this":[71,225],"paradigm.":[73,307],"Firstly,":[74],"may":[78],"hardly":[79],"guarantee":[80],"unbiased":[82],"due":[88],"potential":[90],"mismatching":[91],"with":[92],"test":[94],"data.":[95],"Secondly,":[96],"corresponds":[100],"solve":[102],"complex":[104],"optimization":[105,190,195],"problem,":[106],"which":[107,206],"prone":[109],"getting":[111],"trapped":[112],"into":[113],"inferior":[114],"local":[115,243],"optima":[116,244],"thus":[118],"leads":[119],"undesired":[122],"result.":[124],"To":[125],"address":[126],"these":[127],"issues,":[128],"we":[129],"propose":[130],"novel":[132],"framework.":[135],"It":[136],"generates":[137],"multiple":[138],"pairs":[139],"sets":[144,215],"from":[145,175,216,242,260],"via":[150,188,251],"random":[151],"splitting,":[152],"trains":[153],"pre-specified":[159],"network":[160,172],"structure":[161],"each":[163],"pair":[164],"making":[166],"useful":[168],"knowledge":[169,220],"(e.g.,":[170],"promising":[171],"parameters)":[173],"process":[179,239,259],"be":[181],"transferred":[182],"other":[184,261],"processes":[187],"multi-task":[189],"(i.e.,":[191],"recently":[193],"emerging":[194],"paradigm),":[196],"outputs":[198],"best":[200,210],"one,":[201],"among":[202],"all":[203,217],"models,":[205],"has":[207],"overall":[209],"across":[212],"pairs.":[218],"transfer":[221],"mechanism":[222],"featured":[223],"new":[226],"framework":[227,302],"can":[228],"not":[229],"only":[230],"enhance":[231],"effectiveness":[233],"helping":[235],"escape":[241],"but":[245],"also":[246],"improve":[247],"implicit":[252],"regularization":[253],"imposed":[254],"processes.":[264],"We":[265],"implement":[266],"proposed":[268,301],"framework,":[269],"parallelize":[270],"implementation":[272],"GPU":[275],"cluster,":[276],"apply":[278],"it":[279],"train":[281],"several":[282,290],"widely":[283],"models.":[286],"Experimental":[287],"results":[288],"classification":[291],"datasets":[292],"different":[294],"nature":[295],"demonstrate":[296],"superiority":[298],"over":[303],"conventional":[305]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}