{"id":"https://openalex.org/W4306317445","doi":"https://doi.org/10.1145/3511808.3557575","title":"Data Oversampling with Structure Preserving Variational Learning","display_name":"Data Oversampling with Structure Preserving Variational Learning","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317445","doi":"https://doi.org/10.1145/3511808.3557575"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557575","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"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/A5058474587","display_name":"Indu Solomon","orcid":"https://orcid.org/0000-0002-3490-2796"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Indu Solomon","raw_affiliation_strings":["International Institute of Information Technology Bangalore, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I181514455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083824197","display_name":"J. Senthilnath","orcid":"https://orcid.org/0000-0002-1737-7985"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Senthilnath Jayavelu","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091531578","display_name":"Md Meftahul Ferdaus","orcid":"https://orcid.org/0000-0002-8833-2274"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Md Meftahul Ferdaus","raw_affiliation_strings":["Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033589278","display_name":"Uttam Kumar","orcid":"https://orcid.org/0000-0002-0822-7993"},"institutions":[{"id":"https://openalex.org/I181514455","display_name":"International Institute of Information Technology Bangalore","ror":"https://ror.org/05h9eqy10","country_code":"IN","type":"education","lineage":["https://openalex.org/I181514455"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Uttam Kumar","raw_affiliation_strings":["International Institute of Information Technology Bangalore, Bengaluru, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology Bangalore, Bengaluru, India","institution_ids":["https://openalex.org/I181514455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4490","last_page":"4494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9745000004768372,"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"}},{"id":"https://openalex.org/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.9707000255584717,"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/oversampling","display_name":"Oversampling","score":0.93445885181427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6236661076545715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5577641129493713},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5243687629699707},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5217424631118774},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5083433985710144},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5034114718437195},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4640786647796631},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.4432255029678345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4401247203350067},{"id":"https://openalex.org/keywords/binary-data","display_name":"Binary data","score":0.4300963878631592},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3204955756664276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24140971899032593},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.16097474098205566},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.08398455381393433}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.93445885181427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6236661076545715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5577641129493713},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5243687629699707},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5217424631118774},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5083433985710144},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5034114718437195},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4640786647796631},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.4432255029678345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4401247203350067},{"id":"https://openalex.org/C2779190172","wikidata":"https://www.wikidata.org/wiki/Q4913888","display_name":"Binary data","level":3,"score":0.4300963878631592},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3204955756664276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24140971899032593},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.16097474098205566},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.08398455381393433},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557575","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557575","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1969776092","https://openalex.org/W2087787741","https://openalex.org/W2096945460","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2810282612","https://openalex.org/W2966095869","https://openalex.org/W2981515171","https://openalex.org/W2997068998","https://openalex.org/W4287185050","https://openalex.org/W4308293966"],"related_works":["https://openalex.org/W3196098778","https://openalex.org/W3211250490","https://openalex.org/W4360584310","https://openalex.org/W3080872054","https://openalex.org/W2924282518","https://openalex.org/W2981515171","https://openalex.org/W80466363","https://openalex.org/W3041381337","https://openalex.org/W4382934300","https://openalex.org/W2121061354"],"abstract_inverted_index":{"Traditional":[0],"oversampling":[1,21,66],"methods":[2],"are":[3,93],"well":[4],"explored":[5],"for":[6,20],"binary":[7,139],"and":[8,45,121,140],"multi-class":[9,141],"imbalanced":[10,23],"datasets.":[11],"In":[12],"most":[13],"cases,":[14],"the":[15,22,34,37,83,96,100,103,158,163],"data":[16,41,65,104,146],"space":[17,85,109],"is":[18,114,131],"adapted":[19],"classes.":[24],"It":[25],"leads":[26],"to":[27,50,133],"various":[28,134],"issues":[29],"like":[30],"poor":[31,51],"modelling":[32],"of":[33,36,54,102],"structure":[35,101],"data,":[38,143],"resulting":[39],"in":[40,82,95],"overlapping":[42],"between":[43],"minority":[44,55,91],"majority":[46],"classes":[47,81],"that":[48,157],"lead":[49],"classification":[52],"performance":[53],"class(es).":[56],"To":[57],"overcome":[58],"these":[59],"limitations,":[60],"we":[61],"propose":[62],"a":[63],"novel":[64],"architecture":[67],"called":[68],"Structure":[69],"Preserving":[70],"Variational":[71],"Learning":[72],"(SPVL).":[73],"This":[74],"technique":[75,161],"captures":[76],"an":[77,87,118],"uncorrelated":[78],"distribution":[79,110],"among":[80],"latent":[84,97,108],"using":[86],"encoder-decoder":[88],"framework.":[89],"Hence,":[90],"samples":[92],"generated":[94],"space,":[98],"preserving":[99],"distribution.":[105],"The":[106,127],"improved":[107],"(oversampled":[111],"training":[112,117],"data)":[113],"evaluated":[115],"by":[116],"MLP":[119],"classifier":[120],"testing":[122],"with":[123,137],"unseen":[124],"test":[125],"dataset.":[126],"proposed":[128,159],"SPVL":[129,160],"method":[130],"applied":[132],"benchmark":[135],"datasets":[136],"i)":[138],"imbalance":[142],"ii)":[144],"high-dimensional":[145],"and,":[147],"iii)":[148],"large":[149],"or":[150],"small-scale":[151],"data.":[152],"Extensive":[153],"experimental":[154],"results":[155],"demonstrated":[156],"outperforms":[162],"state-of-the-art":[164],"counterparts.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}