{"id":"https://openalex.org/W4409983098","doi":"https://doi.org/10.1137/1.9781611978520.57","title":"Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation","display_name":"Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409983098","doi":"https://doi.org/10.1137/1.9781611978520.57"},"language":"en","primary_location":{"id":"doi:10.1137/1.9781611978520.57","is_oa":false,"landing_page_url":"https://doi.org/10.1137/1.9781611978520.57","pdf_url":null,"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 2025 SIAM International Conference on Data Mining (SDM)","raw_type":"book-chapter"},"type":"book-chapter","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/A5034671612","display_name":"Muhammad Rajabinasab","orcid":"https://orcid.org/0009-0006-7045-3998"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Muhammad Rajabinasab","raw_affiliation_strings":["University of Southern Denmark, Odense, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093229388","display_name":"Anton D. Lautrup","orcid":"https://orcid.org/0000-0002-9228-2417"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Anton Lautrup","raw_affiliation_strings":["University of Southern Denmark, Odense, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047196019","display_name":"Arthur Zimek","orcid":"https://orcid.org/0000-0001-7713-4208"},"institutions":[{"id":"https://openalex.org/I177969490","display_name":"University of Southern Denmark","ror":"https://ror.org/03yrrjy16","country_code":"DK","type":"education","lineage":["https://openalex.org/I177969490"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Arthur Zimek","raw_affiliation_strings":["University of Southern Denmark, Odense, Denmark"],"affiliations":[{"raw_affiliation_string":"University of Southern Denmark, Odense, Denmark","institution_ids":["https://openalex.org/I177969490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034671612"],"corresponding_institution_ids":["https://openalex.org/I177969490"],"apc_list":null,"apc_paid":null,"fwci":14.7122,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.98683417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"527","last_page":"537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7935000061988831,"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/T10320","display_name":"Neural Networks and Applications","score":0.7935000061988831,"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/similarity","display_name":"Similarity (geometry)","score":0.6579716205596924},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6461772322654724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6427831649780273},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6042737364768982},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5850057601928711},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4510006308555603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44655340909957886},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4063214957714081},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32704800367355347}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6579716205596924},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6461772322654724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6427831649780273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6042737364768982},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5850057601928711},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4510006308555603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44655340909957886},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4063214957714081},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32704800367355347},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/1.9781611978520.57","is_oa":false,"landing_page_url":"https://doi.org/10.1137/1.9781611978520.57","pdf_url":null,"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 2025 SIAM International Conference on Data Mining (SDM)","raw_type":"book-chapter"},{"id":"pmh:oai:sdu.dk:openaire_cris_publications/aa07a380-73ea-4cee-a93b-d1716fb98938","is_oa":false,"landing_page_url":"https://portal.findresearcher.sdu.dk/da/publications/aa07a380-73ea-4cee-a93b-d1716fb98938","pdf_url":null,"source":{"id":"https://openalex.org/S4306400423","display_name":"University of Southern Denmark Research Portal (University of Southern Denmark)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177969490","host_organization_name":"University of Southern Denmark","host_organization_lineage":["https://openalex.org/I177969490"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rajabinasab, M, Lautrup, A & Zimek, A 2025, Metrics for Inter-Dataset Similarity with Example Applications in Synthetic Data and Feature Selection Evaluation. in V Papalexakis, M Riondato, E Zheleva, T Weninger, & W Ding (eds), Proceedings of the 2025 SIAM International Conference on Data Mining (SDM). Society for Industrial and Applied Mathematics, pp. 527-537, 2025 SIAM International Conference on Data Mining, SDM 2025, Alexandria, United States, 01/05/2025. https://doi.org/10.1137/1.9781611978520.57","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2375480909","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2353314428","https://openalex.org/W2012019886","https://openalex.org/W3147584709","https://openalex.org/W2166090428","https://openalex.org/W4386564352","https://openalex.org/W2952668426"],"abstract_inverted_index":{"Measuring":[0],"inter-dataset":[1,23,59],"similarity":[2,24],"is":[3],"an":[4],"important":[5],"task":[6],"in":[7,86,93,106],"machine":[8],"learning":[9],"and":[10,17,34,66,92,102],"data":[11,91],"mining":[12],"with":[13],"various":[14],"use":[15],"cases":[16],"applications.":[18],"Existing":[19],"methods":[20],"for":[21,37,57],"measuring":[22,58],"are":[25],"computationally":[26],"expensive,":[27],"limited,":[28],"or":[29],"sensitive":[30],"to":[31],"different":[32],"entities":[33],"non-trivial":[35],"choices":[36],"parameters.":[38],"They":[39],"also":[40],"lack":[41],"a":[42],"holistic":[43],"perspective":[44],"on":[45],"the":[46,63,67,76,79,87,94,110,113],"entire":[47],"dataset.":[48],"In":[49],"this":[50,107],"paper,":[51],"we":[52],"propose":[53],"two":[54,84],"novel":[55],"metrics":[56,81],"similarity.":[60],"We":[61,74],"discuss":[62],"mathematical":[64],"foundation":[65],"theoretical":[68,101],"basis":[69],"of":[70,78,89,96,112],"our":[71],"proposed":[72,80,114],"metrics.":[73,115],"demonstrate":[75],"effectiveness":[77,111],"by":[82],"investigating":[83],"applications":[85],"evaluation":[88,95],"synthetic":[90],"feature":[97],"selection":[98],"methods.":[99],"The":[100],"empirical":[103],"studies":[104],"conducted":[105],"paper":[108],"illustrate":[109]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-05-01T00:00:00"}