{"id":"https://openalex.org/W2164960226","doi":"https://doi.org/10.14778/1687627.1687711","title":"Mining graph patterns efficiently via randomized summaries","display_name":"Mining graph patterns efficiently via randomized summaries","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2164960226","doi":"https://doi.org/10.14778/1687627.1687711","mag":"2164960226"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687711","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687711","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5100418532","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1013-6932"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chen Chen","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047940824","display_name":"Cindy Xide Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cindy X. Lin","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057424614","display_name":"Matt Fredrikson","orcid":"https://orcid.org/0000-0003-1820-1698"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Fredrikson","raw_affiliation_strings":["University of Wisconsin at Madison"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin at Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050855162","display_name":"Mihai Christodorescu","orcid":"https://orcid.org/0000-0001-5808-8015"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mihai Christodorescu","raw_affiliation_strings":["IBM T. J. Watson Research Center"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047709762","display_name":"Xifeng Yan","orcid":"https://orcid.org/0009-0000-6508-4792"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xifeng Yan","raw_affiliation_strings":["University of California at Santa Barbara"],"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019539533","display_name":"Jiawei Han","orcid":"https://orcid.org/0000-0002-3629-2696"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiawei Han","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100418532"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":12.4208,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.98435186,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"742","last_page":"753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9983999729156494,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.996399998664856,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262246608734131},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5097255110740662},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5079959034919739},{"id":"https://openalex.org/keywords/malware-analysis","display_name":"Malware analysis","score":0.4978160858154297},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4794441759586334},{"id":"https://openalex.org/keywords/malware","display_name":"Malware","score":0.47138696908950806},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47120946645736694},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.459000825881958},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.41598644852638245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21151447296142578},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.164019376039505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262246608734131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5097255110740662},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5079959034919739},{"id":"https://openalex.org/C2779395397","wikidata":"https://www.wikidata.org/wiki/Q15731404","display_name":"Malware analysis","level":3,"score":0.4978160858154297},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4794441759586334},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.47138696908950806},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47120946645736694},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.459000825881958},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.41598644852638245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21151447296142578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.164019376039505},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1687627.1687711","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687711","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.687","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.687","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uiuc.edu/~hanj/pdf/vldb09_cchen.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W4909282","https://openalex.org/W1506285740","https://openalex.org/W1586825695","https://openalex.org/W1592376869","https://openalex.org/W1597561788","https://openalex.org/W1985104873","https://openalex.org/W2019827052","https://openalex.org/W2033252376","https://openalex.org/W2042454716","https://openalex.org/W2064853889","https://openalex.org/W2066506515","https://openalex.org/W2085761620","https://openalex.org/W2101236916","https://openalex.org/W2106072141","https://openalex.org/W2106650313","https://openalex.org/W2108781142","https://openalex.org/W2110034858","https://openalex.org/W2111708605","https://openalex.org/W2125580539","https://openalex.org/W2130990991","https://openalex.org/W2134351561","https://openalex.org/W2136593687","https://openalex.org/W2138745909","https://openalex.org/W2139103617","https://openalex.org/W2145186067","https://openalex.org/W2145771765","https://openalex.org/W2161723275","https://openalex.org/W2162481448","https://openalex.org/W2164281374","https://openalex.org/W2167671111","https://openalex.org/W2168924255","https://openalex.org/W2170726034","https://openalex.org/W2172007538","https://openalex.org/W4252403066","https://openalex.org/W6635637936","https://openalex.org/W6685000865"],"related_works":["https://openalex.org/W4287280928","https://openalex.org/W3178528869","https://openalex.org/W3197146747","https://openalex.org/W2019235339","https://openalex.org/W2057079516","https://openalex.org/W4289244019","https://openalex.org/W2329837696","https://openalex.org/W2345545128","https://openalex.org/W2105037940","https://openalex.org/W2952645149"],"abstract_inverted_index":{"Graphs":[0],"are":[1,201],"prevalent":[2],"in":[3,22,51,65,89,156],"many":[4],"domains":[5],"such":[6],"as":[7],"Bioinformatics,":[8],"social":[9],"networks,":[10],"Web":[11],"and":[12,25,37,116,186],"cyber-security.":[13],"Graph":[14],"pattern":[15,53,214],"mining":[16,41],"has":[17],"become":[18],"an":[19],"important":[20],"tool":[21],"the":[23,52,59,76,103,131,159,165,175,188,194],"management":[24],"analysis":[26],"of":[27,83,114,133,161],"complexly":[28],"structured":[29],"data,":[30],"where":[31,193],"example":[32],"applications":[33],"include":[34],"indexing,":[35],"clustering":[36],"classification.":[38],"Existing":[39],"graph":[40,120],"algorithms":[42],"have":[43],"achieved":[44],"great":[45],"success":[46],"by":[47,148,182],"exploiting":[48],"various":[49],"properties":[50],"space":[54,105],".":[55,106,152],"Unfortunately,":[56],"due":[57],"to":[58,78,100,123,203],"fundamental":[60],"role":[61],"subgraph":[62],"isomorphism":[63],"plays":[64],"these":[66],"methods,":[67],"they":[68],"may":[69],"all":[70,206],"enter":[71],"into":[72],"a":[73,80,112,145],"pitfall":[74],"when":[75],"cost":[77],"enumerate":[79],"huge":[81],"set":[82],"isomorphic":[84],"embeddings":[85],"blows":[86],"up,":[87],"especially":[88],"large":[90],"graphs.":[91],"The":[92],"solution":[93],"we":[94,110],"propose":[95],"for":[96,190],"this":[97,118,139,180],"problem":[98],"resorts":[99],"reduction":[101,126],"on":[102,213,218],"data":[104,125,222],"For":[107],"each":[108],"graph,":[109],"build":[111],"summary":[113],"it":[115],"mine":[117],"shrunk":[119],"instead.":[121],"Compared":[122],"other":[124],"techniques":[127],"that":[128,198,224,235],"either":[129],"reduce":[130],"number":[132],"transactions":[134,151],"or":[135],"compress":[136],"between":[137],"transactions,":[138],"new":[140],"framework,":[141],"called":[142],"Summarize-Mine,":[143],"suggests":[144],"third":[146],"path":[147],"compressing":[149],"within":[150],"Summarize-Mine":[153,225],"is":[154,197,226],"effective":[155],"cutting":[157],"down":[158],"size":[160],"graphs,":[162],"thus":[163],"decreasing":[164],"embedding":[166],"enumeration":[167],"cost.":[168],"However,":[169],"compression":[170],"might":[171],"lose":[172],"patterns":[173,200],"at":[174],"same":[176],"time.":[177],"We":[178,208],"address":[179],"issue":[181],"generating":[183],"randomized":[184],"summaries":[185],"repeating":[187],"process":[189],"multiple":[191],"rounds,":[192],"main":[195],"idea":[196],"true":[199],"unlikely":[202],"miss":[204],"from":[205],"rounds.":[207],"provide":[209],"strict":[210],"probabilistic":[211],"guarantees":[212],"loss":[215],"likelihood.":[216],"Experiments":[217],"real":[219],"malware":[220,233],"trace":[221],"show":[223],"very":[227],"efficient,":[228],"which":[229],"can":[230],"find":[231],"interesting":[232],"fingerprints":[234],"were":[236],"not":[237],"revealed":[238],"previously.":[239]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}