{"id":"https://openalex.org/W3156973762","doi":"https://doi.org/10.1145/3442381.3449984","title":"XY-Sketch: on Sketching Data Streams at Web Scale","display_name":"XY-Sketch: on Sketching Data Streams at Web Scale","publication_year":2021,"publication_date":"2021-04-19","ids":{"openalex":"https://openalex.org/W3156973762","doi":"https://doi.org/10.1145/3442381.3449984","mag":"3156973762"},"language":"en","primary_location":{"id":"doi:10.1145/3442381.3449984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449984","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3442381.3449984","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081609237","display_name":"Yongqiang Liu","orcid":"https://orcid.org/0000-0001-6314-3541"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqiang Liu","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037366245","display_name":"Xike Xie","orcid":"https://orcid.org/0000-0001-5290-5408"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xike Xie","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.6274,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81603964,"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":"1169","last_page":"1180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9987999796867371,"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/T11106","display_name":"Data Management and Algorithms","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/sketch","display_name":"Sketch","score":0.8533375263214111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8181797862052917},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.705802857875824},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5936930179595947},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.5905578136444092},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5678914189338684},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5428760647773743},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4959779679775238},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4904937148094177},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.47496864199638367},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4415532946586609},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43089789152145386},{"id":"https://openalex.org/keywords/dynamic-perfect-hashing","display_name":"Dynamic perfect hashing","score":0.43063879013061523},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.42254048585891724},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3407578766345978},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2882475256919861},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25777751207351685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1814287006855011},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.11147564649581909}],"concepts":[{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.8533375263214111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8181797862052917},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.705802857875824},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5936930179595947},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.5905578136444092},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5678914189338684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5428760647773743},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4959779679775238},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4904937148094177},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.47496864199638367},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4415532946586609},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43089789152145386},{"id":"https://openalex.org/C122907437","wikidata":"https://www.wikidata.org/wiki/Q5318999","display_name":"Dynamic perfect hashing","level":5,"score":0.43063879013061523},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.42254048585891724},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3407578766345978},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2882475256919861},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25777751207351685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1814287006855011},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.11147564649581909},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3442381.3449984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449984","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3442381.3449984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3442381.3449984","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Web Conference 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W151938044","https://openalex.org/W172108465","https://openalex.org/W1493892051","https://openalex.org/W1826290430","https://openalex.org/W1971731845","https://openalex.org/W1977141583","https://openalex.org/W2042518617","https://openalex.org/W2059739152","https://openalex.org/W2060170830","https://openalex.org/W2080234606","https://openalex.org/W2097347451","https://openalex.org/W2112053513","https://openalex.org/W2140960149","https://openalex.org/W2162979096","https://openalex.org/W2169593628","https://openalex.org/W2337280815","https://openalex.org/W2418598077","https://openalex.org/W2423036951","https://openalex.org/W2429183028","https://openalex.org/W2439904216","https://openalex.org/W2544383754","https://openalex.org/W2753629899","https://openalex.org/W2783033738","https://openalex.org/W2797305021","https://openalex.org/W2798533156","https://openalex.org/W2798945787","https://openalex.org/W2864823780","https://openalex.org/W2919413299","https://openalex.org/W2941475075","https://openalex.org/W2965889402","https://openalex.org/W3010602428","https://openalex.org/W4248708867","https://openalex.org/W4249843299"],"related_works":["https://openalex.org/W2811247857","https://openalex.org/W4389449520","https://openalex.org/W2136399778","https://openalex.org/W127192698","https://openalex.org/W102859714","https://openalex.org/W4298343607","https://openalex.org/W2334522381","https://openalex.org/W2040748620","https://openalex.org/W2069197195","https://openalex.org/W1694672787"],"abstract_inverted_index":{"Conventional":[0],"sketching":[1,45,166],"methods":[2],"on":[3,152,165],"counting":[4],"stream":[5],"item":[6,84,91,113],"frequencies":[7],"use":[8],"hash":[9],"functions":[10],"for":[11,133],"mapping":[12],"data":[13,52,62,83,95,112],"items":[14],"to":[15,29,59,160],"a":[16,20,56,72,82,117,130],"concise":[17],"structure,":[18,74],"e.g.,":[19],"two-dimensional":[21],"array,":[22],"at":[23,47,64],"the":[24,33,36,44,48,79,87,94,137,162,181],"expense":[25],"of":[26,51,81,89,103,119,173],"overcounting":[27],"due":[28],"hashing":[30,41],"collisions.":[31],"Despite":[32],"popularity,":[34],"however,":[35],"accumulated":[37],"errors":[38],"originated":[39],"in":[40,93,129],"collisions":[42],"deteriorate":[43],"accuracies":[46],"rapid":[49],"pace":[50],"increasing,":[53],"which":[54,77,124],"poses":[55],"great":[57],"challenge":[58],"sketch":[60],"big":[61],"streams":[63],"web":[65],"scale.":[66],"In":[67],"this":[68,90],"paper,":[69],"we":[70,141],"propose":[71],"novel":[73],"called":[75],"XY-sketch,":[76],"estimates":[78],"frequency":[80],"by":[85],"estimating":[86],"probability":[88],"appearing":[92],"stream.":[96],"The":[97],"framework":[98],"associated":[99],"with":[100],"XY-sketch":[101,170],"consists":[102],"two":[104],"phases,":[105],"namely":[106],"decomposition":[107],"and":[108,147,155],"recomposition":[109,138],"phases.":[110],"A":[111],"is":[114,171,184],"split":[115],"into":[116],"set":[118],"compactly":[120],"stored":[121],"basic":[122],"elements,":[123],"can":[125],"be":[126],"stringed":[127],"up":[128],"probabilistic":[131],"manner":[132],"query":[134],"evaluation":[135],"during":[136],"phase.":[139],"Throughout,":[140],"conduct":[142],"optimization":[143],"under":[144],"space":[145,182],"constraints":[146],"detailed":[148],"theoretical":[149],"analysis.":[150],"Experiments":[151],"both":[153],"real":[154],"synthetic":[156],"datasets":[157],"are":[158],"done":[159],"show":[161],"superior":[163],"scalability":[164],"large-scale":[167],"streams.":[168],"Remarkably,":[169],"orders":[172],"magnitudes":[174],"more":[175],"accurate":[176],"than":[177],"existing":[178],"solutions,":[179],"when":[180],"budget":[183],"small.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}