{"id":"https://openalex.org/W3215543515","doi":"https://doi.org/10.1007/s10618-022-00850-3","title":"EmbAssi: embedding assignment costs for similarity search in large graph databases","display_name":"EmbAssi: embedding assignment costs for similarity search in large graph databases","publication_year":2022,"publication_date":"2022-07-16","ids":{"openalex":"https://openalex.org/W3215543515","doi":"https://doi.org/10.1007/s10618-022-00850-3","mag":"3215543515"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-022-00850-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00850-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00850-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00850-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067340796","display_name":"Franka Bause","orcid":"https://orcid.org/0000-0003-4202-3692"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Franka Bause","raw_affiliation_strings":["Faculty of Computer Science, University of Vienna, Vienna, Austria","UniVie Doctoral School Computer Science, University of Vienna, Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"UniVie Doctoral School Computer Science, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068514720","display_name":"Erich Schubert","orcid":"https://orcid.org/0000-0001-9143-4880"},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Erich Schubert","raw_affiliation_strings":["Department of Computer Science, TU Dortmund University, Dortmund, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9143-4880","affiliations":[{"raw_affiliation_string":"Department of Computer Science, TU Dortmund University, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009569829","display_name":"Nils M. Kriege","orcid":"https://orcid.org/0000-0003-2645-947X"},"institutions":[{"id":"https://openalex.org/I129774422","display_name":"University of Vienna","ror":"https://ror.org/03prydq77","country_code":"AT","type":"education","lineage":["https://openalex.org/I129774422"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Nils M. Kriege","raw_affiliation_strings":["Faculty of Computer Science, University of Vienna, Vienna, Austria","Research Network Data Science, University of Vienna, Vienna, Austria"],"raw_orcid":"https://orcid.org/0000-0003-2645-947X","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]},{"raw_affiliation_string":"Research Network Data Science, University of Vienna, Vienna, Austria","institution_ids":["https://openalex.org/I129774422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009569829","https://openalex.org/A5067340796"],"corresponding_institution_ids":["https://openalex.org/I129774422"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2031,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4455054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"36","issue":"5","first_page":"1728","last_page":"1755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9998999834060669,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9998999834060669,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9976000189781189,"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.9955000281333923,"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/edit-distance","display_name":"Edit distance","score":0.7718928456306458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6306535601615906},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5303201079368591},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4750889837741852},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4535364806652069},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4461916387081146},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4413449764251709},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41142144799232483},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3148239254951477},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26724958419799805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13457408547401428}],"concepts":[{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7718928456306458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6306535601615906},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5303201079368591},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4750889837741852},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4535364806652069},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4461916387081146},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4413449764251709},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41142144799232483},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3148239254951477},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26724958419799805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13457408547401428},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10618-022-00850-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00850-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00850-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2111.07761","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.07761","pdf_url":"https://arxiv.org/pdf/2111.07761","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"doi:10.1007/s10618-022-00850-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00850-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00850-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3988035882","display_name":"SFB 876: Verf\u00fcgbarkeit von Information durch Analyse unter Ressourcenbeschr\u00e4nkung","funder_award_id":"124020371","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5523801029","display_name":null,"funder_award_id":"SFB 876","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5562249194","display_name":"Algorithmic Data Science for Computational Drug Discovery","funder_award_id":"VRG19-009","funder_id":"https://openalex.org/F4320321003","funder_display_name":"Vienna Science and Technology Fund"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"},{"id":"https://openalex.org/F4320321691","display_name":"Universit\u00e4t Wien","ror":"https://ror.org/03prydq77"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3215543515.pdf","grobid_xml":"https://content.openalex.org/works/W3215543515.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W984076445","https://openalex.org/W1597213869","https://openalex.org/W1911005089","https://openalex.org/W1973535531","https://openalex.org/W1983438361","https://openalex.org/W2032338144","https://openalex.org/W2075949491","https://openalex.org/W2120636855","https://openalex.org/W2123838366","https://openalex.org/W2133296809","https://openalex.org/W2134627110","https://openalex.org/W2141461755","https://openalex.org/W2152618599","https://openalex.org/W2164041127","https://openalex.org/W2170607286","https://openalex.org/W2223837972","https://openalex.org/W2436676318","https://openalex.org/W2476974423","https://openalex.org/W2558999090","https://openalex.org/W2615384791","https://openalex.org/W2740161549","https://openalex.org/W2897440725","https://openalex.org/W2906943923","https://openalex.org/W2907492528","https://openalex.org/W2925177113","https://openalex.org/W2928374578","https://openalex.org/W2930082324","https://openalex.org/W2960858043","https://openalex.org/W3003404388","https://openalex.org/W3028737568","https://openalex.org/W3080281801","https://openalex.org/W3103523530","https://openalex.org/W3176961136","https://openalex.org/W3208517188","https://openalex.org/W4230793143","https://openalex.org/W4232849097"],"related_works":["https://openalex.org/W3044917232","https://openalex.org/W1949910768","https://openalex.org/W1480566255","https://openalex.org/W2254397067","https://openalex.org/W2013685631","https://openalex.org/W1516985461","https://openalex.org/W1882921205","https://openalex.org/W2953568333","https://openalex.org/W1974646519","https://openalex.org/W3026218946"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"graph":[2,75,91,170,222],"edit":[3,76,171,179,223],"distance":[4,42,172],"is":[5,18,96,133],"an":[6],"intuitive":[7],"measure":[8],"to":[9,49,66,109,219,232],"quantify":[10],"the":[11,56,68,74,93,130,142,169,178,220],"dissimilarity":[12],"of":[13,51,70,73,144,168],"graphs,":[14],"but":[15],"its":[16],"computation":[17],"$$\\mathsf":[19],"{NP}$$":[20],"<mml:math":[21,151],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\">":[22,152],"<mml:mi>NP</mml:mi>":[23],"</mml:math>":[24,157],"-hard":[25],"and":[26,37,61,201,229],"challenging":[27],"in":[28,92,98],"practice.":[29],"We":[30,53,163],"introduce":[31],"methods":[32],"for":[33,44,81,89,122,184,209],"answering":[34],"nearest":[35],"neighbor":[36],"range":[38],"queries":[39],"regarding":[40],"this":[41,82,115],"efficiently":[43],"large":[45,234],"databases":[46],"with":[47],"up":[48],"millions":[50],"graphs.":[52],"build":[54],"on":[55],"filter-verification":[57,196],"paradigm,":[58],"where":[59,129],"lower":[60,120,166,214],"upper":[62],"bounds":[63,80,107,121,167,215],"are":[64,182,216],"used":[65],"reduce":[67],"number":[69],"exact":[71,221],"computations":[72],"distance.":[77],"Highly":[78],"effective":[79,185,202],"involve":[83],"solving":[84],"a":[85,134,199],"linear":[86],"assignment":[87,127],"problem":[88],"each":[90],"database,":[94],"which":[95,181],"prohibitive":[97],"massive":[99],"datasets.":[100],"Index-based":[101],"approaches":[102],"typically":[103],"provide":[104],"only":[105],"weak":[106],"leading":[108],"high":[110],"computational":[111],"costs":[112,143],"verification.":[113],"In":[114],"work,":[116],"we":[117,206],"derive":[118],"novel":[119],"efficient":[123,160],"filtering":[124],"from":[125,174],"restricted":[126],"problems,":[128],"cost":[131],"function":[132],"tree":[135,175],"metric.":[136],"This":[137],"special":[138],"case":[139],"allows":[140],"embedding":[141],"optimal":[145],"assignments":[146],"isometrically":[147],"into":[148,194],"$$\\ell":[149],"_1$$":[150],"<mml:msub>":[153],"<mml:mi>\u2113</mml:mi>":[154],"<mml:mn>1</mml:mn>":[155],"</mml:msub>":[156],"space,":[158],"rendering":[159],"indexing":[161],"possible.":[162],"propose":[164],"several":[165],"obtained":[173],"metrics":[176],"reflecting":[177],"costs,":[180],"combined":[183],"filtering.":[186],"Our":[187],"method":[188],"termed":[189],"EmbAssi":[190],"can":[191],"be":[192],"integrated":[193],"existing":[195],"pipelines":[197],"as":[198],"fast":[200],"pre-filtering":[203],"step.":[204],"Empirically":[205],"show":[207],"that":[208],"many":[210],"real-world":[211],"graphs":[212],"our":[213,226],"already":[217],"close":[218],"distance,":[224],"while":[225],"index":[227],"construction":[228],"search":[230],"scales":[231],"very":[233],"databases.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2021-12-06T00:00:00"}