{"id":"https://openalex.org/W4206297651","doi":"https://doi.org/10.1016/j.knosys.2021.108075","title":"Mixhead: Breaking the low-rank bottleneck in multi-head attention language models","display_name":"Mixhead: Breaking the low-rank bottleneck in multi-head attention language models","publication_year":2022,"publication_date":"2022-01-05","ids":{"openalex":"https://openalex.org/W4206297651","doi":"https://doi.org/10.1016/j.knosys.2021.108075"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2021.108075","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"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":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-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/A5100350973","display_name":"Zhong Zhang","orcid":"https://orcid.org/0000-0003-1349-9755"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I3018263800","display_name":"Huzhou University","ror":"https://ror.org/04mvpxy20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3018263800"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, 611731, PR China","Yangtze Delta Region Institute (Huzhou) of UESTC, Huzhou, 313000, PR China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, 611731, PR China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Yangtze Delta Region Institute (Huzhou) of UESTC, Huzhou, 313000, PR China","institution_ids":["https://openalex.org/I3018263800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101841879","display_name":"Nian Shao","orcid":"https://orcid.org/0000-0002-6260-3005"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nian Shao","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068892996","display_name":"Chongming Gao","orcid":"https://orcid.org/0000-0002-5187-9196"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongming Gao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, 230026, PR China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, 230026, PR China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036927614","display_name":"Rui Miao","orcid":"https://orcid.org/0000-0002-2917-2311"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Miao","raw_affiliation_strings":["Guizhou University, Guiyang, 550025, PR China"],"affiliations":[{"raw_affiliation_string":"Guizhou University, Guiyang, 550025, PR China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015410049","display_name":"Qinli Yang","orcid":"https://orcid.org/0000-0001-8966-6762"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I3018263800","display_name":"Huzhou University","ror":"https://ror.org/04mvpxy20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3018263800"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinli Yang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, 611731, PR China","Yangtze Delta Region Institute (Huzhou) of UESTC, Huzhou, 313000, PR China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, 611731, PR China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Yangtze Delta Region Institute (Huzhou) of UESTC, Huzhou, 313000, PR China","institution_ids":["https://openalex.org/I3018263800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041619142","display_name":"Junming Shao","orcid":"https://orcid.org/0000-0002-6022-428X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I3018263800","display_name":"Huzhou University","ror":"https://ror.org/04mvpxy20","country_code":"CN","type":"education","lineage":["https://openalex.org/I3018263800"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junming Shao","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, 611731, PR China","Yangtze Delta Region Institute (Huzhou) of UESTC, Huzhou, 313000, PR China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, 611731, PR China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Yangtze Delta Region Institute (Huzhou) of UESTC, Huzhou, 313000, PR China","institution_ids":["https://openalex.org/I3018263800"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041619142"],"corresponding_institution_ids":["https://openalex.org/I150229711","https://openalex.org/I3018263800"],"apc_list":{"value":3130,"currency":"USD","value_usd":3130,"provenance":"doaj"},"apc_paid":null,"fwci":1.297,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.99997,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":90},"biblio":{"volume":"240","issue":null,"first_page":"108075","last_page":"108075"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998,"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/T10028","display_name":"Topic Modeling","score":0.9998,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9902,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9889,"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/overfitting","display_name":"Overfitting","score":0.7647897},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.53308654}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8091582},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7647897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534755},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6070129},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5495863},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.53308654},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5014837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45622855},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4144609},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39983064},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34346795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15634486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07877034},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2021.108075","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"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":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.78,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"52079026"},{"funder":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China","award_id":"61976044"},{"funder":"https://openalex.org/F4320328119","funder_display_name":"National University's Basic Research Foundation of China","award_id":null},{"funder":"https://openalex.org/F4320333335","funder_display_name":"Sichuan Province Science and Technology Support Program","award_id":"2020YFH0037"},{"funder":"https://openalex.org/F4320334945","funder_display_name":"Fok Ying Tong Education Foundation","award_id":"161062"},{"funder":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities","award_id":"ZYGX2019Z014"}],"datasets":[],"versions":[],"referenced_works_count":27,"referenced_works":["https://openalex.org/W2068238590","https://openalex.org/W2150884987","https://openalex.org/W2167905000","https://openalex.org/W2194775991","https://openalex.org/W2611669587","https://openalex.org/W2767989436","https://openalex.org/W2888799392","https://openalex.org/W2923014074","https://openalex.org/W2933138175","https://openalex.org/W2962822108","https://openalex.org/W2963748441","https://openalex.org/W2964110616","https://openalex.org/W2971351900","https://openalex.org/W2972324944","https://openalex.org/W2979826702","https://openalex.org/W2984100107","https://openalex.org/W3015468748","https://openalex.org/W3021293129","https://openalex.org/W3023360076","https://openalex.org/W3033529678","https://openalex.org/W3033893309","https://openalex.org/W3036939249","https://openalex.org/W3047554829","https://openalex.org/W3096609285","https://openalex.org/W3097065222","https://openalex.org/W3134929386","https://openalex.org/W4323654151"],"related_works":["https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4221142204","https://openalex.org/W2922073769","https://openalex.org/W2794347674","https://openalex.org/W2490526372","https://openalex.org/W1574414179"],"abstract_inverted_index":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4206297651","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2025-01-05T04:12:00.649680","created_date":"2022-01-25"}