{"id":"https://openalex.org/W3118434586","doi":"https://doi.org/10.1145/3444370.3444605","title":"From One-hot Encoding to Privacy-preserving Synthetic Electronic Health Records Embedding","display_name":"From One-hot Encoding to Privacy-preserving Synthetic Electronic Health Records Embedding","publication_year":2020,"publication_date":"2020-12-04","ids":{"openalex":"https://openalex.org/W3118434586","doi":"https://doi.org/10.1145/3444370.3444605","mag":"3118434586"},"language":"en","primary_location":{"id":"doi:10.1145/3444370.3444605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3444370.3444605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies","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/A5089748803","display_name":"Xiayu Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiayu Xiang","raw_affiliation_strings":["School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086035676","display_name":"Shaoming Duan","orcid":"https://orcid.org/0000-0002-7546-9562"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoming Duan","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023954747","display_name":"Hezhong Pan","orcid":"https://orcid.org/0000-0003-3364-6855"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hezhong Pan","raw_affiliation_strings":["School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086732255","display_name":"Peiyi Han","orcid":"https://orcid.org/0000-0002-3845-7749"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyi Han","raw_affiliation_strings":["School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046947918","display_name":"Jiahao Cao","orcid":"https://orcid.org/0000-0001-7139-376X"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Cao","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103171964","display_name":"Chuanyi Liu","orcid":"https://orcid.org/0000-0002-9846-9709"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanyi Liu","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China and Cyberspace Security Center, Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China and Cyberspace Security Center, Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"407","last_page":"413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","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/T10764","display_name":"Privacy-Preserving Technologies in Data","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/T13702","display_name":"Machine Learning in Healthcare","score":0.9972000122070312,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9690999984741211,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7804774045944214},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7674894332885742},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7076655626296997},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.617104172706604},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5824335217475891},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5039536356925964},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4720267355442047},{"id":"https://openalex.org/keywords/information-sensitivity","display_name":"Information sensitivity","score":0.4678918421268463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4487072229385376},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4440368711948395},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4413532018661499},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.43734002113342285},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.42627355456352234},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.39315566420555115},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3865126371383667},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.32248014211654663},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11129269003868103}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804774045944214},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7674894332885742},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7076655626296997},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.617104172706604},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5824335217475891},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5039536356925964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4720267355442047},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.4678918421268463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4487072229385376},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4440368711948395},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4413532018661499},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.43734002113342285},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.42627355456352234},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39315566420555115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3865126371383667},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32248014211654663},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11129269003868103},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3444370.3444605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3444370.3444605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 International Conference on Cyberspace Innovation of Advanced Technologies","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":23,"referenced_works":["https://openalex.org/W2014226385","https://openalex.org/W2051267297","https://openalex.org/W2094791001","https://openalex.org/W2104167780","https://openalex.org/W2239904484","https://openalex.org/W2284851926","https://openalex.org/W2295598076","https://openalex.org/W2460445187","https://openalex.org/W2565167788","https://openalex.org/W2596378825","https://openalex.org/W2765449478","https://openalex.org/W2799900537","https://openalex.org/W2949346884","https://openalex.org/W2963693643","https://openalex.org/W2963841265","https://openalex.org/W3004195290","https://openalex.org/W3015471667","https://openalex.org/W3037567775","https://openalex.org/W3080136191","https://openalex.org/W3099785009","https://openalex.org/W3102476541","https://openalex.org/W3121797687","https://openalex.org/W3123159599"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W3199964822","https://openalex.org/W4232132981","https://openalex.org/W4238046985","https://openalex.org/W3164948662","https://openalex.org/W3003242282","https://openalex.org/W3153597579","https://openalex.org/W3012824888","https://openalex.org/W2998249245"],"abstract_inverted_index":{"Categorical":[0],"Encoding,":[1],"typically":[2],"one-hot":[3,82,127],"encoding,":[4],"plays":[5],"a":[6,81,91,134,183,204],"central":[7],"role":[8],"when":[9],"we":[10],"learn":[11],"Machine":[12],"Learning":[13],"models.":[14],"This":[15],"classic":[16],"approach":[17],"is":[18,48,122,137],"the":[19,29,51,104,109,112,131,140,147],"most":[20],"prevalent":[21],"strategy":[22],"due":[23],"to":[24,40,65,72],"its":[25,59,192],"simplicity.":[26],"However,":[27],"as":[28,90,130,203],"number":[30],"of":[31,53,77,84,108,133,142,149,186],"categories":[32],"grows":[33],"large":[34],"and":[35,57,211],"sparse,":[36],"it":[37,43],"becomes":[38],"infeasible":[39],"train":[41],"since":[42],"creates":[44],"high-dimensional":[45],"vectors,":[46],"which":[47,96,199],"also":[49,116],"at":[50],"risk":[52],"revealing":[54],"private":[55],"information":[56,156],"breaking":[58],"underlying":[60],"structure.":[61],"We":[62],"here":[63],"propose":[64],"utilize":[66],"data":[67,79,162,197],"intermediate":[68],"representation":[69],"learning":[70,210],"(embedding)":[71],"overcome":[73],"such":[74],"limitations.":[75],"Instead":[76],"representing":[78],"with":[80],"vector":[83,94],"many":[85],"cardinalities,":[86],"an":[87],"embedding":[88,121],"serves":[89],"lower-dimensional":[92],"dense":[93],"in":[95,111],"each":[97],"cell":[98],"can":[99,115],"contain":[100],"any":[101],"number,":[102],"capturing":[103],"latent":[105],"hierarchical":[106],"structures":[107],"features":[110,171],"meantime.":[113],"It":[114],"be":[117],"assumed":[118],"that":[119,168],"sharing":[120],"safer":[123],"than":[124],"releasing":[125],"raw":[126],"encoded":[128],"data,":[129],"presence":[132],"particular":[135],"feature":[136],"represented":[138],"by":[139,159,190],"value":[141],"1,":[143],"otherwise":[144],"0.":[145],"With":[146],"assist":[148],"Generative":[150],"Adversarial":[151],"Network":[152],"further":[153],"alleviates":[154],"sensitive":[155],"leakage":[157],"issue":[158],"creating":[160],"synthetic":[161],"for":[163,207],"modeling.":[164],"Our":[165],"result":[166],"suggests":[167],"even":[169],"embedded":[170],"may":[172],"more":[173],"or":[174],"less":[175],"pose":[176],"privacy":[177],"flaws,":[178],"deploying":[179],"GAN":[180],"will":[181],"make":[182],"wider":[184],"variety":[185],"medical":[187,208],"datasets":[188],"available":[189],"retaining":[191],"relative":[193],"utility":[194],"while":[195],"preserving":[196],"privacy,":[198],"has":[200],"been":[201],"identified":[202],"promising":[205],"method":[206],"machine":[209],"prediction.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}