{"id":"https://openalex.org/W3080130308","doi":"https://doi.org/10.1145/3394486.3403187","title":"Catalysis Clustering with GAN by Incorporating Domain Knowledge","display_name":"Catalysis Clustering with GAN by Incorporating Domain Knowledge","publication_year":2020,"publication_date":"2020-08-20","ids":{"openalex":"https://openalex.org/W3080130308","doi":"https://doi.org/10.1145/3394486.3403187","mag":"3080130308"},"language":"en","primary_location":{"id":"doi:10.1145/3394486.3403187","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/A5042252323","display_name":"Olga Andreeva","orcid":"https://orcid.org/0000-0002-1784-0335"},"institutions":[{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olga Andreeva","raw_affiliation_strings":["University of Massachusetts Boston, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Boston, Boston, MA, USA","institution_ids":["https://openalex.org/I33434090"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318161","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-3135-0447"},"institutions":[{"id":"https://openalex.org/I111599522","display_name":"Jiangnan University","ror":"https://ror.org/04mkzax54","country_code":"CN","type":"education","lineage":["https://openalex.org/I111599522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Jiangnan University & Jiangsu Key Laboratory of Media Design and Software Technology, Wuxi, Jiangsu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangnan University & Jiangsu Key Laboratory of Media Design and Software Technology, Wuxi, Jiangsu, China","institution_ids":["https://openalex.org/I111599522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088432110","display_name":"Wei Ding","orcid":"https://orcid.org/0000-0002-3383-551X"},"institutions":[{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Ding","raw_affiliation_strings":["University of Massachusetts Boston, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Boston, Boston, MA, USA","institution_ids":["https://openalex.org/I33434090"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081799863","display_name":"Marieke L. Kuijjer","orcid":"https://orcid.org/0000-0001-6280-3130"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Marieke Kuijjer","raw_affiliation_strings":["University of Oslo, Oslo, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084245470","display_name":"John Quackenbush","orcid":"https://orcid.org/0000-0002-2702-5879"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Quackenbush","raw_affiliation_strings":["Harvard T. H. Chan School of Public Health, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard T. H. Chan School of Public Health, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100400329","display_name":"Ping Chen","orcid":"https://orcid.org/0000-0003-3789-7686"},"institutions":[{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ping Chen","raw_affiliation_strings":["University of Massachusetts Boston, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Boston, Boston, MA, USA","institution_ids":["https://openalex.org/I33434090"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1344","last_page":"1352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9954000115394592,"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":0.9944999814033508,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8936525583267212},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7043440341949463},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.6785329580307007},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6346741914749146},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.561428964138031},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.5318498015403748},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.5128815174102783},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.488830029964447},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.48439842462539673},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.47747373580932617},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4742932617664337},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.42912936210632324},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.41912779211997986},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4165690243244171},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3711045980453491},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1736086905002594}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8936525583267212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7043440341949463},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.6785329580307007},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6346741914749146},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.561428964138031},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.5318498015403748},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.5128815174102783},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.488830029964447},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.48439842462539673},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.47747373580932617},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4742932617664337},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.42912936210632324},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.41912779211997986},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4165690243244171},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3711045980453491},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1736086905002594},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394486.3403187","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394486.3403187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1519425500","https://openalex.org/W1966331733","https://openalex.org/W1967278811","https://openalex.org/W1977556410","https://openalex.org/W2041440766","https://openalex.org/W2098812767","https://openalex.org/W2118978333","https://openalex.org/W2121906867","https://openalex.org/W2123696077","https://openalex.org/W2129281854","https://openalex.org/W2132791018","https://openalex.org/W2148143831","https://openalex.org/W2487878123","https://openalex.org/W2623607951","https://openalex.org/W2910641067","https://openalex.org/W2948398419","https://openalex.org/W2963761396","https://openalex.org/W4230962320"],"related_works":["https://openalex.org/W2163563073","https://openalex.org/W4301002638","https://openalex.org/W2188840951","https://openalex.org/W3146523624","https://openalex.org/W3186815950","https://openalex.org/W2564198485","https://openalex.org/W2202413591","https://openalex.org/W3124860551","https://openalex.org/W2311450085","https://openalex.org/W2309230723"],"abstract_inverted_index":{"Clustering":[0,144],"is":[1,12,70,84,94,123,212],"an":[2],"important":[3],"unsupervised":[4],"learning":[5],"method":[6],"with":[7,21],"serious":[8],"challenges":[9,122],"when":[10,91,175],"data":[11,46,73,93,167],"sparse":[13],"and":[14,34,54,72,87,103,128,169,189,214,221],"high-dimensional.":[15],"Generated":[16],"clusters":[17,104,193,217],"are":[18,100,159,194,199,219],"often":[19],"evaluated":[20],"general":[22],"measures,":[23],"which":[24,158],"may":[25],"not":[26,110],"be":[27],"meaningful":[28,220],"or":[29],"useful":[30,222],"for":[31,223],"practical":[32],"applications":[33],"domains.":[35],"Using":[36],"a":[37,40,80,139,178],"distance":[38,82,98],"metric,":[39],"clustering":[41,132,151,173,184],"algorithm":[42],"searches":[43],"through":[44],"the":[45,66,131,150,165],"space,":[47],"groups":[48],"close":[49],"items":[50],"into":[51,130,149],"one":[52],"cluster,":[53],"assigns":[55],"far":[56],"away":[57],"samples":[58],"to":[59,114,119,124,145,171],"different":[60],"clusters.":[61],"In":[62,134],"many":[63],"real-world":[64,205,224],"applications,":[65],"number":[67],"of":[68,79],"dimensions":[69],"high":[71],"space":[74],"becomes":[75,88],"very":[76,85],"sparse.":[77],"Selection":[78],"suitable":[81],"metric":[83],"difficult":[86],"even":[89],"harder":[90],"categorical":[92],"involved.":[95],"Moreover,":[96],"existing":[97],"metrics":[99],"mostly":[101],"generic,":[102],"created":[105],"based":[106],"on":[107,202],"them":[108],"will":[109],"necessarily":[111],"make":[112],"sense":[113],"domain-specific":[115,179],"applications.":[116,225],"One":[117],"option":[118],"address":[120],"these":[121],"integrate":[125],"domain-defined":[126],"rules":[127],"guidelines":[129],"process.":[133,152],"this":[135],"work":[136],"we":[137,155],"propose":[138],"GAN-based":[140],"approach":[141,211],"called":[142],"Catalysis":[143],"incorporate":[146],"domain":[147],"knowledge":[148],"With":[153],"GANs":[154],"generate":[156,216],"catalysts,":[157],"special":[160],"synthetic":[161],"points":[162,198],"drawn":[163],"from":[164],"original":[166],"distribution":[168],"verified":[170],"improve":[172],"quality":[174],"measured":[176],"by":[177],"metric.":[180],"We":[181],"then":[182],"perform":[183],"analysis":[185],"using":[186],"both":[187],"catalysts":[188],"real":[190],"data.":[191],"Final":[192],"produced":[195],"after":[196],"catalyst":[197],"removed.":[200],"Experiments":[201],"two":[203],"challenging":[204],"datasets":[206],"clearly":[207],"show":[208],"that":[209,218],"our":[210],"effective":[213],"can":[215]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}