{"id":"https://openalex.org/W4415230071","doi":"https://doi.org/10.1609/aies.v8i1.36604","title":"Dataset-to-Dataset Evaluation Before (and Without) Sharing Data","display_name":"Dataset-to-Dataset Evaluation Before (and Without) Sharing Data","publication_year":2025,"publication_date":"2025-10-15","ids":{"openalex":"https://openalex.org/W4415230071","doi":"https://doi.org/10.1609/aies.v8i1.36604"},"language":"en","primary_location":{"id":"doi:10.1609/aies.v8i1.36604","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36604","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36604/38742","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ojs.aaai.org/index.php/AIES/article/download/36604/38742","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116235538","display_name":"Keren Fuentes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keren Fuentes","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074869445","display_name":"Mimee Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mimee Xu","raw_affiliation_strings":["New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081135036","display_name":"Irene Y. Chen","orcid":"https://orcid.org/0000-0001-5202-2111"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Irene Y. Chen","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37319566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"1","first_page":"963","last_page":"977"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.17440000176429749,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.17440000176429749,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14280","display_name":"Big Data Technologies and Applications","score":0.15530000627040863,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6678000092506409},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4668000042438507},{"id":"https://openalex.org/keywords/data-source","display_name":"Data source","score":0.41990000009536743},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.39899998903274536},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.3813000023365021},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.3499000072479248},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7059000134468079},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6678000092506409},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.47859999537467957},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42800000309944153},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4124999940395355},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40389999747276306},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aies.v8i1.36604","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36604","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36604/38742","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/36604","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AIES/article/view/36604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"3065-8365","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aies.v8i1.36604","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aies.v8i1.36604","pdf_url":"https://ojs.aaai.org/index.php/AIES/article/download/36604/38742","source":{"id":"https://openalex.org/S5407048695","display_name":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","issn_l":"3065-8365","issn":["3065-8365"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415230071.pdf","grobid_xml":"https://content.openalex.org/works/W4415230071.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Privacy":[0],"concerns":[1],"and":[2,43,89,146,160],"competitive":[3],"interests":[4],"impede":[5],"data":[6,40,57,112,150,172],"access":[7],"for":[8,100],"machine":[9],"learning,":[10],"due":[11],"to":[12,15,29,54,81,108],"the":[13,96],"inability":[14],"privately":[16],"assess":[17,55],"external":[18,39,56],"data's":[19],"utility.":[20],"This":[21,75],"dynamic":[22],"disadvantages":[23],"smaller":[24],"organizations":[25],"that":[26,52,168,178],"lack":[27],"resources":[28],"aggressively":[30],"pursue":[31],"data-sharing":[32],"agreements.":[33],"In":[34],"data-limited":[35],"scenarios,":[36],"not":[37],"all":[38,129],"is":[41],"beneficial,":[42],"collaborations":[44,151],"suffer":[45],"especially":[46],"in":[47,152],"heavily":[48],"regulated":[49],"domains:":[50],"metrics":[51,124],"aim":[53],"given":[58],"a":[59,82,116],"source":[60,117],"e.g.,":[61],"approximating":[62],"their":[63],"KL-divergence,":[64],"require":[65],"accessing":[66],"samples":[67],"from":[68],"both":[69],"entities":[70],"pre-collaboration,":[71],"hence":[72],"violating":[73],"privacy.":[74],"conundrum":[76],"disempowers":[77],"legitimate":[78],"data-sharing,":[79],"leading":[80],"false":[83],"``privacy-utility":[84],"trade-off\".":[85],"To":[86],"resolve":[87],"privacy":[88,105],"uncertainty":[90],"tensions":[91],"simultaneously,":[92],"we":[93],"introduce":[94],"SecureKL,":[95],"first":[97],"secure":[98,169],"protocol":[99],"dataset-to-dataset":[101],"evaluations":[102],"with":[103,126,143],"zero":[104],"leakage,":[106],"designed":[107],"be":[109],"applied":[110],"preceding":[111],"sharing.":[113],"SecureKL":[114,137],"evaluates":[115],"dataset":[118,122],"against":[119],"candidates,":[120],"performing":[121],"divergence":[123],"internally":[125],"private":[127],"computations,":[128],"without":[130],"assuming":[131],"downstream":[132],"models.":[133],"On":[134],"real-world":[135],"data,":[136],"achieves":[138],"high":[139],"consistency":[140],"(>90%":[141],"correlation":[142],"non-private":[144],"counterparts)":[145],"successfully":[147],"identifies":[148],"beneficial":[149],"highly-heterogeneous":[153],"domains":[154],"(ICU":[155],"mortality":[156],"prediction":[157,162],"across":[158,163],"hospitals":[159],"income":[161],"states).":[164],"Our":[165],"results":[166],"highlight":[167],"computation":[170],"maximizes":[171],"utilization,":[173],"outperforming":[174],"privacy-agnostic":[175],"utility":[176],"assessments":[177],"leak":[179],"information.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-16T00:00:00"}