{"id":"https://openalex.org/W3012955081","doi":"https://doi.org/10.1137/1.9781611976236.35","title":"Global-and-Local Aware Data Generation for the Class Imbalance Problem","display_name":"Global-and-Local Aware Data Generation for the Class Imbalance Problem","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3012955081","doi":"https://doi.org/10.1137/1.9781611976236.35","mag":"3012955081"},"language":"en","primary_location":{"id":"doi:10.1137/1.9781611976236.35","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611976236.35","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611976236.35","source":{"id":"https://openalex.org/S4306463922","display_name":"Society for Industrial and Applied Mathematics eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 SIAM International Conference on Data Mining","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611976236.35","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100394126","display_name":"Wentao Wang","orcid":"https://orcid.org/0000-0001-9919-7488"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wentao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011048500","display_name":"Suhang Wang","orcid":"https://orcid.org/0000-0003-3448-4878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suhang Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043696243","display_name":"Wenqi Fan","orcid":"https://orcid.org/0000-0002-4049-1233"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqi Fan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014957271","display_name":"Zitao Liu","orcid":"https://orcid.org/0000-0003-0491-307X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zitao Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040639891","display_name":"Jiliang Tang","orcid":"https://orcid.org/0000-0001-7125-3898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiliang Tang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100394126"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8714,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.92432823,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"307","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9955999851226807,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.9575222730636597},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7786351442337036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605808734893799},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6569527387619019},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5854442119598389},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.54563307762146},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5383777022361755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5155529975891113},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4616040587425232},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34734252095222473}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9575222730636597},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7786351442337036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605808734893799},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6569527387619019},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5854442119598389},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.54563307762146},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5383777022361755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5155529975891113},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4616040587425232},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34734252095222473},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/1.9781611976236.35","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611976236.35","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611976236.35","source":{"id":"https://openalex.org/S4306463922","display_name":"Society for Industrial and Applied Mathematics eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 SIAM International Conference on Data Mining","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1137/1.9781611976236.35","is_oa":true,"landing_page_url":"https://doi.org/10.1137/1.9781611976236.35","pdf_url":"https://epubs.siam.org/doi/pdf/10.1137/1.9781611976236.35","source":{"id":"https://openalex.org/S4306463922","display_name":"Society for Industrial and Applied Mathematics eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 SIAM International Conference on Data Mining","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012955081.pdf","grobid_xml":"https://content.openalex.org/works/W3012955081.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2185967890","https://openalex.org/W2297432279"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W4206637278","https://openalex.org/W2781247653","https://openalex.org/W4386005305","https://openalex.org/W3082051559","https://openalex.org/W1682621979","https://openalex.org/W4386214543","https://openalex.org/W1969988626","https://openalex.org/W3173198409","https://openalex.org/W2300921526"],"abstract_inverted_index":{"In":[0],"many":[1],"real-world":[2],"classification":[3,208],"applications":[4],"such":[5,35],"as":[6,23,36],"fake":[7],"news":[8],"detection,":[9],"the":[10,24,28,43,56,96,110,124,151,168,192,207],"training":[11,215],"data":[12,65,83,106,112,126,189],"can":[13,72,176],"be":[14,177],"extremely":[15,181],"imbalanced,":[16],"which":[17,71,149],"brings":[18],"challenges":[19],"to":[20,41,131,154,166],"existing":[21,59],"classifiers":[22,212],"majority":[25,57,88,140],"classes":[26],"dominate":[27],"loss":[29],"functions":[30],"of":[31,58,194,210],"classifiers.":[32],"Oversampling":[33],"techniques":[34],"SMOTE":[37,152],"are":[38],"effective":[39],"approaches":[40],"tackle":[42],"class":[44,97],"imbalance":[45,98],"problem":[46,99],"by":[47,100],"producing":[48,199],"more":[49],"synthetic":[50,173],"minority":[51,69,76,120,174,203],"samples.":[52],"Despite":[53],"their":[54],"success,":[55],"oversampling":[60],"methods":[61],"only":[62],"consider":[63],"local":[64,103,111,156],"distributions":[66,84],"when":[67],"generating":[68,119,133],"samples,":[70],"result":[73],"in":[74,91,158,198],"noisy":[75],"samples":[77,136,175,204],"that":[78,137,172],"do":[79],"not":[80],"fit":[81],"global":[82,105,125,169],"or":[85,135],"interleave":[86,138],"with":[87,139],"classes.":[89,141],"Hence,":[90],"this":[92],"paper,":[93],"we":[94,143],"study":[95],"simultaneously":[101],"exploring":[102],"and":[104,122,163,201],"information":[107,117],"since:":[108],"(i)":[109],"distribution":[113,127,157],"could":[114,128],"give":[115],"detailed":[116],"for":[118,205],"samples;":[121],"(ii)":[123],"provide":[129],"guidance":[130],"avoid":[132],"outliers":[134],"Specifically,":[142],"propose":[144],"a":[145,159],"novel":[146],"framework":[147,197],"GL-GAN,":[148],"leverages":[150],"method":[153],"explore":[155],"learned":[160],"latent":[161],"space":[162],"employs":[164],"GAN":[165],"capture":[167],"information,":[170],"so":[171],"generated":[178],"under":[179],"even":[180],"imbalanced":[182,214],"scenarios.":[183],"Experimental":[184],"results":[185],"on":[186,213],"diverse":[187],"real":[188],"sets":[190],"demonstrate":[191],"effectiveness":[193],"our":[195],"GL-GAN":[196],"realistic":[200],"discriminative":[202],"improving":[206],"performance":[209],"various":[211],"data.":[216],"Our":[217],"code":[218],"is":[219],"available":[220],"at":[221],"https://github.com/wentao-repo/GL-GAN.":[222]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}