{"id":"https://openalex.org/W2808744076","doi":"https://doi.org/10.1145/3219819.3220085","title":"Node Similarity with q -Grams for Real-World Labeled Networks","display_name":"Node Similarity with q -Grams for Real-World Labeled Networks","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2808744076","doi":"https://doi.org/10.1145/3219819.3220085","mag":"2808744076"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3220085","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3220085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dl.acm.org/doi/10.1145/3219819.3220085","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086573637","display_name":"Alessio Conte","orcid":"https://orcid.org/0000-0003-0770-2235"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Alessio Conte","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","NII - National Institute of Informatics (2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430 - Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"NII - National Institute of Informatics (2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430 - Japan)","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072066218","display_name":"Gaspare Ferraro","orcid":"https://orcid.org/0000-0003-3146-9293"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gaspare Ferraro","raw_affiliation_strings":["University of Pisa, Pisa, Italy","DI - Dipartimento di Informatica [Pisa] (University of Pisa Dipartimento di Informatica Largo B. Pontecorvo, 3 (formerly via F. Buonarroti, 2) I-56127 Pisa - Italy)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"DI - Dipartimento di Informatica [Pisa] (University of Pisa Dipartimento di Informatica Largo B. Pontecorvo, 3 (formerly via F. Buonarroti, 2) I-56127 Pisa - Italy)","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006984021","display_name":"Roberto Grossi","orcid":"https://orcid.org/0000-0002-7985-4222"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Roberto Grossi","raw_affiliation_strings":["University of Pisa, Pisa, Italy","DI - Dipartimento di Informatica [Pisa] (University of Pisa Dipartimento di Informatica Largo B. Pontecorvo, 3 (formerly via F. Buonarroti, 2) I-56127 Pisa - Italy)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"DI - Dipartimento di Informatica [Pisa] (University of Pisa Dipartimento di Informatica Largo B. Pontecorvo, 3 (formerly via F. Buonarroti, 2) I-56127 Pisa - Italy)","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035852380","display_name":"Andrea Marino","orcid":"https://orcid.org/0000-0002-9854-7885"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Marino","raw_affiliation_strings":["University of Pisa, Pisa, Italy","DI - Dipartimento di Informatica [Pisa] (University of Pisa Dipartimento di Informatica Largo B. Pontecorvo, 3 (formerly via F. Buonarroti, 2) I-56127 Pisa - Italy)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa, Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]},{"raw_affiliation_string":"DI - Dipartimento di Informatica [Pisa] (University of Pisa Dipartimento di Informatica Largo B. Pontecorvo, 3 (formerly via F. Buonarroti, 2) I-56127 Pisa - Italy)","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077610103","display_name":"Kunihiko Sadakane","orcid":"https://orcid.org/0000-0002-8212-3682"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunihiko Sadakane","raw_affiliation_strings":["University of Tokyo, Tokyo, Japan","Tokyo University of Science [Tokyo] (6-3-1 Niijuku Katsushika-Ku, Tokyo 125-8585 Japan - Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Tokyo University of Science [Tokyo] (6-3-1 Niijuku Katsushika-Ku, Tokyo 125-8585 Japan - Japan)","institution_ids":["https://openalex.org/I161296585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076101253","display_name":"Takeaki Uno","orcid":"https://orcid.org/0000-0001-7274-279X"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeaki Uno","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","NII - National Institute of Informatics (2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430 - Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"NII - National Institute of Informatics (2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430 - Japan)","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4432,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.83006284,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1282","last_page":"1291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10374","display_name":"Advanced Graph Theory Research","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/jaccard-index","display_name":"Jaccard index","score":0.9498854875564575},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5706334710121155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.541157603263855},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5397945046424866},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5315560698509216},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43685781955718994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4273946285247803},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38577523827552795},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.36130666732788086},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3385658264160156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2792835831642151},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2277248501777649}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.9498854875564575},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5706334710121155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.541157603263855},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5397945046424866},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5315560698509216},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43685781955718994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4273946285247803},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38577523827552795},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.36130666732788086},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3385658264160156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2792835831642151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2277248501777649},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3219819.3220085","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3220085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01964716v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-01964716","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"KDD 2018 - ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug 2018, London, United Kingdom. pp.1282-1291, ⟨10.1145/3219819.3220085⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arpi.unipi.it:11568/959925","is_oa":true,"landing_page_url":"https://dl.acm.org/doi/10.1145/3219819.3220085","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:flore.unifi.it:2158/1149232","is_oa":false,"landing_page_url":"http://hdl.handle.net/2158/1149232","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arpi.unipi.it:11568/959925","is_oa":true,"landing_page_url":"https://dl.acm.org/doi/10.1145/3219819.3220085","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7940165753","display_name":"Theory and Practice of Succinct Data Structures","funder_award_id":"16H02781","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W103340358","https://openalex.org/W1967863517","https://openalex.org/W1977998106","https://openalex.org/W1979104937","https://openalex.org/W1980074516","https://openalex.org/W2011039300","https://openalex.org/W2024988577","https://openalex.org/W2026417691","https://openalex.org/W2037705937","https://openalex.org/W2039688703","https://openalex.org/W2069153192","https://openalex.org/W2097921823","https://openalex.org/W2101092380","https://openalex.org/W2117831564","https://openalex.org/W2126907894","https://openalex.org/W2133299088","https://openalex.org/W2137874581","https://openalex.org/W2148885851","https://openalex.org/W2155461593","https://openalex.org/W2164053284","https://openalex.org/W2241571695","https://openalex.org/W2296148711","https://openalex.org/W2441800701","https://openalex.org/W2604248105","https://openalex.org/W2604272474","https://openalex.org/W2605174772","https://openalex.org/W2901157541","https://openalex.org/W2963919031"],"related_works":["https://openalex.org/W1994775821","https://openalex.org/W2012019886","https://openalex.org/W2091133150","https://openalex.org/W2945869148","https://openalex.org/W2611195251","https://openalex.org/W2398781203","https://openalex.org/W2009279505","https://openalex.org/W4206503171","https://openalex.org/W4366711670","https://openalex.org/W2972216353"],"abstract_inverted_index":{"We":[0,78,114],"study":[1],"node":[2,87],"similarity":[3,88],"in":[4,12,27],"labeled":[5,49],"networks,":[6,38],"using":[7],"the":[8,20,24,32,39,43,69,106],"label":[9],"sequences":[10],"found":[11],"paths":[13,50],"of":[14,45,68,83,96,108],"bounded":[15],"length":[16],"q":[17],"leading":[18],"to":[19,37,65,110,128],"nodes.":[21],"(This":[22],"recalls":[23],"q-grams":[25,46],"employed":[26],"document":[28],"resemblance,":[29],"based":[30,91],"on":[31,92],"Jaccard":[33,70],"distance.)":[34],"When":[35],"applied":[36],"challenge":[40],"is":[41,112,121],"two-fold:":[42],"number":[44],"generated":[47],"from":[48],"grows":[51],"exponentially":[52],"with":[53,89,130],"q,":[54],"and":[55,102,123],"their":[56],"frequency":[57],"should":[58],"be":[59],"taken":[60],"into":[61],"account:":[62],"this":[63],"leads":[64],"a":[66,81,93],"variation":[67],"index":[71,75],"known":[72],"as":[73],"Bray-Curtis":[74],"for":[76,86],"multisets.":[77],"describe":[79],"nSimGram,":[80],"suite":[82],"fast":[84],"algorithms":[85],"q-grams,":[90],"novel":[94],"blend":[95],"color":[97],"coding,":[98],"probabilistic":[99],"counting,":[100],"sketches,":[101],"string":[103],"algorithms,":[104],"where":[105],"universe":[107],"elements":[109],"sample":[111],"exponential.":[113],"provide":[115],"experimental":[116],"evidence":[117],"that":[118],"our":[119,124],"measure":[120],"effective":[122],"running":[125],"times":[126],"scale":[127],"deal":[129],"large":[131],"real-world":[132],"networks.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}