{"id":"https://openalex.org/W7168078343","doi":"https://doi.org/10.1007/978-981-92-2864-5_3","title":"Reducing Redundancy in\u00a0Multi-Head Attention via\u00a0Diversity Regularization","display_name":"Reducing Redundancy in\u00a0Multi-Head Attention via\u00a0Diversity Regularization","publication_year":2026,"publication_date":"2026-07-12","ids":{"openalex":"https://openalex.org/W7168078343","doi":"https://doi.org/10.1007/978-981-92-2864-5_3"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-2864-5_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-2864-5_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5029779245","display_name":"Kejie Hu","orcid":"https://orcid.org/0000-0002-9644-4188"},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejie Hu","raw_affiliation_strings":["City University of Wu Han, Wuhan, 430083, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Wu Han, Wuhan, 430083, Hubei, China","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123968173","display_name":"F T Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210100789","display_name":"Wuhan College","ror":"https://ror.org/01dashf18","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210100789"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fang Liu","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, 430072, Hubei, China","Wuhan Software Engineering Vocational College (Wuhan Open University), Wuhan, 430083, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, 430072, Hubei, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Wuhan Software Engineering Vocational College (Wuhan Open University), Wuhan, 430083, Hubei, China","institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210100789"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140500500","display_name":"Bing Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Zhou","raw_affiliation_strings":["City University of Wu Han, Wuhan, 430083, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"City University of Wu Han, Wuhan, 430083, Hubei, China","institution_ids":["https://openalex.org/I75900474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5123968173"],"corresponding_institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210100789"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.22179999947547913,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T14347","display_name":"Big Data and Digital Economy","score":0.22179999947547913,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.13670000433921814,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.08609999716281891,"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/bottleneck","display_name":"Bottleneck","score":0.7448999881744385},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.7182000279426575},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7161999940872192},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.460099995136261},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44929999113082886},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.38960000872612},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.31610000133514404},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.3127000033855438}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8719000220298767},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7448999881744385},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.7182000279426575},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7161999940872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612000226974487},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5067999958992004},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.28850001096725464},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-2864-5_3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-2864-5_3","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7489785552024841,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2946794439","https://openalex.org/W3082034060","https://openalex.org/W3131922516","https://openalex.org/W3138516171","https://openalex.org/W3153880451","https://openalex.org/W3174396451","https://openalex.org/W4313007769","https://openalex.org/W4382239070","https://openalex.org/W4385299278","https://openalex.org/W4391021637","https://openalex.org/W4409248487"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-07-13T00:00:00"}