{"id":"https://openalex.org/W3145060834","doi":"https://doi.org/10.1109/tkde.2021.3069861","title":"LDA-Reg: Knowledge Driven Regularization Using External Corpora","display_name":"LDA-Reg: Knowledge Driven Regularization Using External Corpora","publication_year":2021,"publication_date":"2021-03-31","ids":{"openalex":"https://openalex.org/W3145060834","doi":"https://doi.org/10.1109/tkde.2021.3069861","mag":"3145060834"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3069861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3069861","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","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/A5037185687","display_name":"Kai Yang","orcid":"https://orcid.org/0000-0002-6371-7741"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Yang","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027609768","display_name":"Zhaojing Luo","orcid":"https://orcid.org/0000-0001-7271-3999"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhaojing Luo","raw_affiliation_strings":["Department of Computer Science, Schoool of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7271-3999","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Schoool of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000935850","display_name":"Jinyang Gao","orcid":"https://orcid.org/0000-0001-8247-1196"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jinyang Gao","raw_affiliation_strings":["Department of Computer Science, Schoool of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Schoool of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009946754","display_name":"Junfeng Zhao","orcid":"https://orcid.org/0000-0002-1268-5006"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Zhao","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024892041","display_name":"Beng Chin Ooi","orcid":"https://orcid.org/0000-0003-4446-1100"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Beng Chin Ooi","raw_affiliation_strings":["Department of Computer Science, Schoool of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-4446-1100","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Schoool of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102928967","display_name":"Bing Xie","orcid":"https://orcid.org/0000-0002-2988-2575"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Xie","raw_affiliation_strings":["School of Electronic Engineering and Computer Science, Peking University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037185687"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.3998,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84611781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"34","issue":"12","first_page":"5840","last_page":"5853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9990000128746033,"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":0.998199999332428,"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":0.8448886871337891},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6852068901062012},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6591067314147949},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5772644877433777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5755935907363892},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.5606445074081421},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5415338277816772},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.5408800840377808},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4796905219554901},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4710158109664917},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.45016416907310486},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.44681504368782043},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.42134255170822144},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.27269211411476135},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.09010133147239685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448886871337891},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6852068901062012},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6591067314147949},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5772644877433777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5755935907363892},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.5606445074081421},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5415338277816772},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5408800840377808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4796905219554901},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4710158109664917},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.45016416907310486},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.44681504368782043},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42134255170822144},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.27269211411476135},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.09010133147239685},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2021.3069861","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3069861","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1094757534","display_name":null,"funder_award_id":"AISG-GC-2019-002","funder_id":"https://openalex.org/F4320320709","funder_display_name":"National Research Foundation Singapore"}],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1502706994","https://openalex.org/W1862694079","https://openalex.org/W1981617416","https://openalex.org/W2044185127","https://openalex.org/W2095705004","https://openalex.org/W2107743791","https://openalex.org/W2110591510","https://openalex.org/W2113459411","https://openalex.org/W2117539524","https://openalex.org/W2140190241","https://openalex.org/W2144513243","https://openalex.org/W2147152072","https://openalex.org/W2163455955","https://openalex.org/W2163922914","https://openalex.org/W2250539671","https://openalex.org/W2250753706","https://openalex.org/W2325227998","https://openalex.org/W2396881363","https://openalex.org/W2558960030","https://openalex.org/W2787883929","https://openalex.org/W2794455536","https://openalex.org/W2886201417","https://openalex.org/W2946273655","https://openalex.org/W2952478253","https://openalex.org/W2952810773","https://openalex.org/W2963626623","https://openalex.org/W2998704965","https://openalex.org/W3003973800","https://openalex.org/W3080628425","https://openalex.org/W3176730989","https://openalex.org/W3176739743","https://openalex.org/W4231510805","https://openalex.org/W4293568472","https://openalex.org/W4294170691","https://openalex.org/W6639619044","https://openalex.org/W6674330103","https://openalex.org/W6676781583","https://openalex.org/W6676984168","https://openalex.org/W6680532216","https://openalex.org/W6681151457","https://openalex.org/W6682691769","https://openalex.org/W6685802191","https://openalex.org/W6712503630","https://openalex.org/W6719819555","https://openalex.org/W6734688555","https://openalex.org/W6764819356"],"related_works":["https://openalex.org/W3134737443","https://openalex.org/W2989932438","https://openalex.org/W4323060038","https://openalex.org/W2792987183","https://openalex.org/W2909157681","https://openalex.org/W2787191226","https://openalex.org/W2790173704","https://openalex.org/W3180274546","https://openalex.org/W4307074408","https://openalex.org/W3145060834"],"abstract_inverted_index":{"While":[0],"recent":[1],"developments":[2],"of":[3,13,21,42,110,157],"neural":[4,58],"network":[5,59],"(NN)":[6],"models":[7],"have":[8],"led":[9],"to":[10,50,89,94,101,130],"a":[11,26,33,39,74,138],"series":[12],"record-breaking":[14],"achievements":[15],"in":[16],"many":[17],"applications,":[18],"the":[19,52,90,103,107,111,146,155],"lack":[20],"sufficiently":[22],"good":[23],"datasets":[24],"remains":[25],"problem":[27],"for":[28,65,145,197],"some":[29],"applications.":[30],"For":[31,106],"such":[32,66],"problem,":[34],"we":[35,71,113,135],"can":[36],"however":[37],"exploit":[38],"large":[40],"number":[41],"unstructured":[43],"text":[44],"corpora":[45],"as":[46,86],"an":[47,87,116,162],"external":[48,98],"knowledge":[49,76,99],"complement":[51],"training":[53],"data,":[54],"and":[55,100,125,141,149,169,194],"most":[56],"prevailing":[57],"solutions":[60],"employ":[61],"word":[62,91,187],"embedding":[63,92,188],"methods":[64,93,189],"purposes.":[67],"In":[68],"this":[69],"paper,":[70],"propose":[72,114],"LDA-Reg,":[73],"novel":[75],"driven":[77],"regularization":[78,159],"framework":[79,160,179],"based":[80],"on":[81],"Latent":[82],"Dirichlet":[83],"Allocation":[84],"(LDA)":[85],"alternative":[88],"adaptively":[95],"utilize":[96],"abundant":[97],"interpret":[102],"NN":[104],"model.":[105],"joint":[108],"learning":[109],"parameters,":[112],"EM-SGD,":[115],"effective":[117],"update":[118,131,140,143],"method":[119,144],"which":[120],"incorporates":[121],"Expectation":[122],"Maximization":[123],"(EM)":[124],"Stochastic":[126],"Gradient":[127],"Descent":[128],"(SGD)":[129],"parameters":[132],"iteratively.":[133],"Moreover,":[134],"also":[136,191],"devise":[137],"lazy":[139],"sparse":[142,150],"high-dimensional":[147],"inputs":[148,151],"respectively.":[152],"We":[153],"validate":[154],"effectiveness":[156],"our":[158,177],"through":[161],"extensive":[163],"experimental":[164],"study":[165],"over":[166,185],"real":[167],"world":[168],"standard":[170],"benchmark":[171],"datasets.":[172],"The":[173],"results":[174],"show":[175],"that":[176],"proposed":[178],"not":[180],"only":[181],"achieves":[182],"significant":[183,195],"improvement":[184],"state-of-the-art":[186],"but":[190],"learns":[192],"interpretable":[193],"topics":[196],"various":[198],"tasks.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}