{"id":"https://openalex.org/W4400969791","doi":"https://doi.org/10.1145/3682112.3682115","title":"Synthetic data for learning-based knowledge discovery","display_name":"Synthetic data for learning-based knowledge discovery","publication_year":2024,"publication_date":"2024-07-24","ids":{"openalex":"https://openalex.org/W4400969791","doi":"https://doi.org/10.1145/3682112.3682115"},"language":"en","primary_location":{"id":"doi:10.1145/3682112.3682115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3682112.3682115","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","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/A5022498356","display_name":"William Shiao","orcid":"https://orcid.org/0000-0001-5813-2266"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Shiao","raw_affiliation_strings":["University of California, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054849323","display_name":"Evangelos E. Papalexakis","orcid":"https://orcid.org/0000-0002-3411-8483"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos E. Papalexakis","raw_affiliation_strings":["University of California, Riverside, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Riverside, CA, USA","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I103635307"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08899618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":"1","first_page":"19","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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":0.9986000061035156,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9983000159263611,"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":0.7624673843383789},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7217259407043457},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.649787187576294},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5884501338005066},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5151528120040894},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4919557273387909},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4829842150211334},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4488457143306732},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.42299336194992065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7624673843383789},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7217259407043457},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.649787187576294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5884501338005066},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5151528120040894},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4919557273387909},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4829842150211334},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4488457143306732},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.42299336194992065},{"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:10.1145/3682112.3682115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3682112.3682115","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-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/W1947476231","https://openalex.org/W2130072301","https://openalex.org/W2148143831","https://openalex.org/W2571268788","https://openalex.org/W3005680577","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3080274717","https://openalex.org/W3210036019","https://openalex.org/W4283319085","https://openalex.org/W4298289240","https://openalex.org/W4306316942","https://openalex.org/W4312933868","https://openalex.org/W4318822975","https://openalex.org/W4319586039","https://openalex.org/W4380558608","https://openalex.org/W4386027279","https://openalex.org/W6637568146"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W3037187668","https://openalex.org/W2611989081","https://openalex.org/W4234772502","https://openalex.org/W4230611425","https://openalex.org/W2731899572","https://openalex.org/W2380685755","https://openalex.org/W4294635752","https://openalex.org/W4304166257","https://openalex.org/W4380075502"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,23,36,62,69],"deep":[3],"learning":[4],"have":[5,39],"demonstrated":[6,22],"the":[7,31,53,63,70,87,103,112,115],"ability":[8],"of":[9,114,122,130],"learning-based":[10,45,96],"methods":[11],"to":[12,30,93,111],"tackle":[13],"very":[14],"hard":[15,50],"downstream":[16],"tasks.":[17],"Historically,":[18],"this":[19,81],"has":[20],"been":[21],"predictive":[24],"tasks,":[25],"while":[26],"tasks":[27],"more":[28],"akin":[29],"traditional":[32],"KDD":[33,54],"(Knowledge":[34],"Discovery":[35],"Databases)":[37],"pipeline":[38],"enjoyed":[40],"proportionally":[41],"fewer":[42],"advances.":[43],"Can":[44],"approaches":[46],"help":[47],"with":[48],"inherently":[49],"problems":[51],"within":[52],"pipeline,":[55],"such":[56],"as":[57],"\"how":[58,73],"many":[59],"patterns":[60],"are":[61,66],"data\",":[64,71],"\"what":[65],"different":[67],"structures":[68],"and":[72,117,127],"can":[74],"we":[75,84,118],"robustly":[76],"extract":[77],"those":[78],"structures?\"":[79],"In":[80],"vision":[82],"paper,":[83],"argue":[85],"for":[86,89,98,132],"need":[88],"synthetic":[90],"data":[91],"generators":[92],"empower":[94],"cheaply-supervised":[95],"solutions":[97],"knowledge":[99],"discovery.":[100],"We":[101],"describe":[102],"general":[104],"idea,":[105],"early":[106],"proof-of-concept":[107],"results":[108],"which":[109],"speak":[110],"viability":[113],"paradigm,":[116],"outline":[119],"a":[120,128],"number":[121],"exciting":[123],"challenges":[124],"that":[125],"await,":[126],"set":[129],"milestones":[131],"measuring":[133],"success.":[134]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}