{"id":"https://openalex.org/W7140298745","doi":"https://doi.org/10.1016/j.neucom.2026.133408","title":"Revisiting data imbalance in token-based self-supervised learning","display_name":"Revisiting data imbalance in token-based self-supervised learning","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140298745","doi":"https://doi.org/10.1016/j.neucom.2026.133408"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133408","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133408","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-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/A5044851404","display_name":"Daeyoung Han","orcid":"https://orcid.org/0000-0003-0368-8675"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeyoung Han","raw_affiliation_strings":["The School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0368-8675","affiliations":[{"raw_affiliation_string":"The School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130578444","display_name":"Hyung Rok Jung","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung Rok Jung","raw_affiliation_strings":["The Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130621395","display_name":"Tianhong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianhong Li","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, Massachusetts, United States of America","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052959289","display_name":"Dina Katabi","orcid":"https://orcid.org/0000-0003-4854-4157"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dina Katabi","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar Street, Cambridge, 02139, Massachusetts, United States of America","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112688924","display_name":"Jeany Son","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeany Son","raw_affiliation_strings":["Graduate School of AI and Computer Science & Engineering, Pohang University of Science and Technology, 77 Cheongam-ro, Nam-gu, Pohang, 37673, Gyeongsangbuk-do, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of AI and Computer Science & Engineering, Pohang University of Science and Technology, 77 Cheongam-ro, Nam-gu, Pohang, 37673, Gyeongsangbuk-do, Republic of Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085604883","display_name":"Hong Kook Kim","orcid":"https://orcid.org/0000-0002-0105-6693"},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hong kook Kim","raw_affiliation_strings":["The Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea","The School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Artificial Intelligence Graduate School, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]},{"raw_affiliation_string":"The School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126353261","display_name":"Moongu Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I39534123","display_name":"Gwangju Institute of Science and Technology","ror":"https://ror.org/024kbgz78","country_code":"KR","type":"education","lineage":["https://openalex.org/I39534123"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Moongu Jeon","raw_affiliation_strings":["The School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-2775-7789","affiliations":[{"raw_affiliation_string":"The School of Electrical Engineering and Computer Science, Gwangju Institute of Science and Technology, 123 Cheomdangwagi-ro, Buk-gu, Gwangju, 61005, Republic of Korea","institution_ids":["https://openalex.org/I39534123"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5126353261"],"corresponding_institution_ids":["https://openalex.org/I39534123"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.60299781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"682","issue":null,"first_page":"133408","last_page":"133408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6685000061988831,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6685000061988831,"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":0.17489999532699585,"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":0.014999999664723873,"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/smoothing","display_name":"Smoothing","score":0.6575999855995178},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6355000138282776},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6072999835014343},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.519599974155426},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5063999891281128},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.48820000886917114},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4530999958515167},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4472000002861023},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4422000050544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800000011920929},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6575999855995178},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6355000138282776},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5788999795913696},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5063999891281128},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.48820000886917114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4837000072002411},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4472000002861023},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4422000050544739},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3711000084877014},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133408","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133408","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7811297178268433,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2112020727","https://openalex.org/W2118978333","https://openalex.org/W2120838001","https://openalex.org/W2166049352","https://openalex.org/W2435090885","https://openalex.org/W2750378047","https://openalex.org/W3021199811","https://openalex.org/W3108417339","https://openalex.org/W4285295719","https://openalex.org/W4366352743"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-03-26T00:00:00"}
