{"id":"https://openalex.org/W3135915160","doi":"https://doi.org/10.1109/bigdata50022.2020.9377843","title":"Sketch and Scale Geo-distributed tSNE and UMAP","display_name":"Sketch and Scale Geo-distributed tSNE and UMAP","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3135915160","doi":"https://doi.org/10.1109/bigdata50022.2020.9377843","mag":"3135915160"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-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/A5069796188","display_name":"Viska Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Viska Wei","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013689256","display_name":"Nikita Ivkin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nikita Ivkin","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053736722","display_name":"Vladimir Braverman","orcid":"https://orcid.org/0000-0001-7709-8753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladimir Braverman","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019891335","display_name":"Alexander S. Szalay","orcid":"https://orcid.org/0000-0002-4108-3282"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander S. Szalay","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069796188"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.3908,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63680514,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"996","last_page":"1003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10799","display_name":"Data Visualization and Analytics","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9771999716758728,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11164","display_name":"Remote Sensing and LiDAR Applications","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental 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":0.7955945134162903},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.5097712874412537},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4763489067554474},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.475948303937912},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.47388333082199097},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.437224805355072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25645649433135986},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21664127707481384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955945134162903},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.5097712874412537},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4763489067554474},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.475948303937912},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.47388333082199097},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.437224805355072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25645649433135986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21664127707481384}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","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":40,"referenced_works":["https://openalex.org/W1493892051","https://openalex.org/W1875842236","https://openalex.org/W1956690708","https://openalex.org/W1965972569","https://openalex.org/W1995484833","https://openalex.org/W2001141328","https://openalex.org/W2016289973","https://openalex.org/W2040387238","https://openalex.org/W2053186076","https://openalex.org/W2054002066","https://openalex.org/W2080234606","https://openalex.org/W2080745194","https://openalex.org/W2134312057","https://openalex.org/W2157444450","https://openalex.org/W2157988812","https://openalex.org/W2187089797","https://openalex.org/W2255388164","https://openalex.org/W2487095677","https://openalex.org/W2766030723","https://openalex.org/W2786672974","https://openalex.org/W2795228480","https://openalex.org/W2885520603","https://openalex.org/W2970421227","https://openalex.org/W2994280181","https://openalex.org/W2996250107","https://openalex.org/W3043574444","https://openalex.org/W3103325675","https://openalex.org/W3104183086","https://openalex.org/W4238172360","https://openalex.org/W4249843299","https://openalex.org/W4287720355","https://openalex.org/W4288417148","https://openalex.org/W6629496199","https://openalex.org/W6683161245","https://openalex.org/W6683501082","https://openalex.org/W6691787250","https://openalex.org/W6748816842","https://openalex.org/W6749784662","https://openalex.org/W6761040187","https://openalex.org/W6780897730"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2392363776","https://openalex.org/W2063051341","https://openalex.org/W2591066345","https://openalex.org/W1494563618","https://openalex.org/W2357022711"],"abstract_inverted_index":{"Running":[0],"machine":[1],"learning":[2],"analytics":[3],"over":[4],"geographically":[5],"distributed":[6],"datasets":[7,149],"is":[8,74],"a":[9,46,79,88],"rapidly":[10],"arising":[11],"problem":[12],"in":[13,56,137,140],"the":[14,95,98,102,107,117,120,125,164,168,201],"world":[15],"of":[16,66,155,170,187,193],"data":[17,23,28,50,68,91,96,156,161,178,192],"management":[18],"policies":[19],"ensuring":[20],"privacy":[21],"and":[22,38,42,58,83,110,142,190],"security.":[24],"Visualizing":[25],"high":[26],"dimensional":[27],"using":[29],"tools":[30,53],"such":[31],"as":[32],"t-distributed":[33],"Stochastic":[34],"Neighbor":[35],"Embedding":[36],"(tSNE)":[37],"Uniform":[39],"Manifold":[40],"Approximation":[41],"Projection":[43],"(UMAP)":[44],"became":[45],"common":[47],"practice":[48],"for":[49],"scientists.":[51],"Both":[52],"scale":[54,135],"poorly":[55],"time":[57],"memory.":[59],"While":[60],"recent":[61],"optimizations":[62],"showed":[63],"successful":[64],"handling":[65],"10,000":[67],"points,":[69,157],"scaling":[70],"beyond":[71],"million":[72,181,195],"points":[73],"still":[75],"challenging.":[76],"We":[77,166],"introduce":[78],"novel":[80],"framework:":[81],"Sketch":[82,90],"Scale":[84],"(SnS).":[85],"It":[86],"leverages":[87],"Count":[89],"structure":[92],"to":[93,131,147],"compress":[94],"on":[97,106,116,173],"edge":[99],"nodes,":[100],"aggregates":[101],"reduced":[103],"size":[104],"sketches":[105],"master":[108],"node,":[109],"runs":[111],"vanilla":[112],"tSNE":[113],"or":[114],"UMAP":[115],"summary,":[118],"representing":[119],"densest":[121],"areas,":[122],"extracted":[123],"from":[124,184,200],"aggregated":[126],"sketch.We":[127],"show":[128],"this":[129],"technique":[130],"be":[132],"fully":[133],"parallel,":[134],"linearly":[136],"time,":[138],"logarithmically":[139],"memory":[141],"communication,":[143],"making":[144],"it":[145],"possible":[146],"analyze":[148],"with":[150,179,197],"many":[151],"millions,":[152],"potentially":[153],"billions":[154],"spread":[158],"across":[159],"several":[160],"centers":[162],"around":[163],"globe.":[165],"demonstrate":[167],"power":[169],"our":[171],"method":[172],"two":[174],"mid-size":[175],"datasets:":[176],"cancer":[177],"52":[180],"35-band":[182],"pixels":[183],"multiplex":[185],"images":[186],"tumor":[188],"biopsies;":[189],"astrophysics":[191],"100":[194],"stars":[196],"multi-color":[198],"photometry":[199],"Sloan":[202],"Digital":[203],"Sky":[204],"Survey":[205],"(SDSS).":[206]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}