{"id":"https://openalex.org/W3090427676","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207520","title":"Latent space decomposition into task-specific and domain-specific subspaces for domain adaptation","display_name":"Latent space decomposition into task-specific and domain-specific subspaces for domain adaptation","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090427676","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207520","mag":"3090427676"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207520","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":"article","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/A5044233433","display_name":"Takaya Ueda","orcid":"https://orcid.org/0000-0001-5715-1609"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takaya Ueda","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078994792","display_name":"Ikuko Nishikawa","orcid":"https://orcid.org/0000-0003-4780-0155"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ikuko Nishikawa","raw_affiliation_strings":["Ritsumeikan University, Shiga, Japan"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University, Shiga, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044233433"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63574981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"80","issue":null,"first_page":"1","last_page":"7"},"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":0.9997000098228455,"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9884999990463257,"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/T10028","display_name":"Topic Modeling","score":0.9829999804496765,"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/linear-subspace","display_name":"Linear subspace","score":0.6900438666343689},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6704176068305969},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6629737615585327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6403051614761353},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.61009281873703},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5665712952613831},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5101075768470764},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.49752357602119446},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4173818826675415},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33126023411750793},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3166760504245758},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22693735361099243}],"concepts":[{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6900438666343689},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6704176068305969},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6629737615585327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6403051614761353},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.61009281873703},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5665712952613831},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5101075768470764},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.49752357602119446},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4173818826675415},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33126023411750793},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3166760504245758},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22693735361099243},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207520","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1565327149","https://openalex.org/W1731081199","https://openalex.org/W1956343362","https://openalex.org/W1959608418","https://openalex.org/W2112796928","https://openalex.org/W2159291411","https://openalex.org/W2187089797","https://openalex.org/W2335728318","https://openalex.org/W2478454054","https://openalex.org/W2584009249","https://openalex.org/W2593768305","https://openalex.org/W2739748921","https://openalex.org/W2953127297","https://openalex.org/W2962808524","https://openalex.org/W2963217615","https://openalex.org/W2963446520","https://openalex.org/W4289490880","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6633949838","https://openalex.org/W6637618735","https://openalex.org/W6640850671","https://openalex.org/W6640963894","https://openalex.org/W6683633756","https://openalex.org/W6688325169","https://openalex.org/W6703116779","https://openalex.org/W6721237847","https://openalex.org/W6725448924","https://openalex.org/W6734335776","https://openalex.org/W6735913928","https://openalex.org/W6738077463","https://openalex.org/W6741832134","https://openalex.org/W6746282794","https://openalex.org/W6754215057"],"related_works":["https://openalex.org/W3100286349","https://openalex.org/W2896134808","https://openalex.org/W4289378085","https://openalex.org/W4294291164","https://openalex.org/W3172436493","https://openalex.org/W1887135636","https://openalex.org/W4287164812","https://openalex.org/W2386063599","https://openalex.org/W1975884855","https://openalex.org/W3213150849"],"abstract_inverted_index":{"In":[0,154],"this":[1],"study,":[2],"we":[3],"propose":[4],"a":[5,30,38,63,87,102,113,116,124,129,258],"novel":[6],"method":[7,106,256],"of":[8,14,19,180,209,218],"acquiring":[9],"the":[10,26,42,50,55,72,78,82,92,96,139,155,181,184,196,199,219,224,228,232,236,240,250],"latent":[11,39,44,73,141],"space":[12,45,74,118,131,222,234],"(composed":[13],"task-specific":[15,88,117,165,221,251],"and":[16,52,163,167],"domain-specific":[17,103,130,169,233],"subspaces)":[18],"data.":[20,177],"The":[21,105,143,216,242],"layered":[22],"neural":[23],"networks":[24],"acquire":[25,71],"effective":[27],"features":[28,79,93],"for":[29],"given":[31],"task":[32,51,83,197],"in":[33,75,86,101,119,138],"its":[34,120,135],"internal":[35],"layers":[36],"as":[37,134,212],"space.":[40,142],"If":[41],"acquired":[43],"is":[46,69,132,145],"relevant":[47,80,94],"only":[48],"to":[49,54,62,70,81,95,173,190,194,227,239,245],"invariant":[53],"data":[56,97,160,186],"domain,":[57],"it":[58],"can":[59],"be":[60,191],"adapted":[61],"new":[64],"domain.":[65,200],"Therefore,":[66],"our":[67,255],"goal":[68],"which":[76],"all":[77,91],"are":[84,99,161,171,203],"contained":[85,100],"subspace,":[89],"whereas":[90,231],"domain":[98,243],"subspace.":[104],"iterates":[107],"two":[108,158,164,168,175],"simple":[109],"training":[110,150,179],"steps.":[111],"First,":[112],"classifier":[114,182],"acquires":[115],"final":[121],"layer":[122],"through":[123],"conventional":[125],"supervised":[126],"learning.":[127],"Whereas":[128],"obtained":[133,220,253],"complementary":[136],"subspace":[137,189],"complete":[140],"latter":[144],"realized":[146],"by":[147,254],"an":[148,246,262],"autoencoder":[149],"using":[151,183,249],"both":[152],"subspaces.":[153],"second":[156],"step,":[157],"input":[159],"used,":[162],"representations":[166,170],"exchanged":[172],"generate":[174],"composite":[176,185],"Further":[178],"forces":[187],"each":[188],"more":[192],"specific":[193],"either":[195],"or":[198],"Computer":[201],"experiments":[202],"conducted":[204],"on":[205],"three":[206,213],"famous":[207],"datasets":[208],"handwritten":[210],"digits":[211],"different":[214],"domains.":[215],"visualization":[217],"shows":[223,235],"clusters":[225],"corresponding":[226,238],"digit":[229],"classes,":[230],"areas":[237],"datasets.":[241],"adaptation":[244],"unlearned":[247],"dataset":[248],"representation":[252],"demonstrates":[257],"higher":[259],"performance":[260],"than":[261],"alternative":[263],"method.":[264]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}