{"id":"https://openalex.org/W2401304055","doi":"https://doi.org/10.1007/978-3-319-28379-1_4","title":"Hashing-Based Hybrid Duplicate Detection for Bayesian Network Structure Learning","display_name":"Hashing-Based Hybrid Duplicate Detection for Bayesian Network Structure Learning","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2401304055","doi":"https://doi.org/10.1007/978-3-319-28379-1_4","mag":"2401304055"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-319-28379-1_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-28379-1_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-319-28379-1_4","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051050720","display_name":"Niklas Jahnsson","orcid":null},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Niklas Jahnsson","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023679130","display_name":"Brandon Malone","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153965","display_name":"Max Planck Institute for Biology of Ageing","ror":"https://ror.org/04xx1tc24","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210153965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Brandon Malone","raw_affiliation_strings":["Max Planck Institute for the Biology of Ageing, Cologne, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for the Biology of Ageing, Cologne, Germany","institution_ids":["https://openalex.org/I4210153965"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069221880","display_name":"Petri Myllym\u00e4ki","orcid":"https://orcid.org/0000-0001-9095-282X"},"institutions":[{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]},{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Petri Myllym\u00e4ki","raw_affiliation_strings":["Helsinki Institute for Information Technology, Esbo, Finland","University of Helsinki, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Helsinki Institute for Information Technology, Esbo, Finland","institution_ids":["https://openalex.org/I32943570"]},{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023679130"],"corresponding_institution_ids":["https://openalex.org/I4210153965"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.3269,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59955909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9998000264167786,"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/T11719","display_name":"Data Quality and Management","score":0.9706000089645386,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9312999844551086,"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/computer-science","display_name":"Computer science","score":0.8080524206161499},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.6393306255340576},{"id":"https://openalex.org/keywords/sorting","display_name":"Sorting","score":0.6129195690155029},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5899048447608948},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5863685607910156},{"id":"https://openalex.org/keywords/bin","display_name":"Bin","score":0.47859618067741394},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4542168080806732},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4339641332626343},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4325748085975647},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.4220644533634186},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.4212251305580139},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.41867393255233765},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3433172106742859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2828595042228699},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.2641577422618866},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.12183016538619995},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11851972341537476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080524206161499},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.6393306255340576},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.6129195690155029},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5899048447608948},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5863685607910156},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.47859618067741394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4542168080806732},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4339641332626343},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4325748085975647},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.4220644533634186},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4212251305580139},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.41867393255233765},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3433172106742859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2828595042228699},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.2641577422618866},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.12183016538619995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11851972341537476},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-319-28379-1_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-28379-1_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-319-28379-1_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-319-28379-1_4","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W46204108","https://openalex.org/W52733133","https://openalex.org/W77740957","https://openalex.org/W104215361","https://openalex.org/W178169250","https://openalex.org/W1517993545","https://openalex.org/W1530964327","https://openalex.org/W1595545560","https://openalex.org/W1692516163","https://openalex.org/W1789238264","https://openalex.org/W1981696983","https://openalex.org/W1998698985","https://openalex.org/W2008906462","https://openalex.org/W2010288201","https://openalex.org/W2011039300","https://openalex.org/W2046915582","https://openalex.org/W2096053066","https://openalex.org/W2106240601","https://openalex.org/W2110915140","https://openalex.org/W2118196167","https://openalex.org/W2122410182","https://openalex.org/W2133476056","https://openalex.org/W2159080219","https://openalex.org/W2169152096","https://openalex.org/W2170112109","https://openalex.org/W2171053395","https://openalex.org/W2182389258","https://openalex.org/W2199532448","https://openalex.org/W2249676289","https://openalex.org/W2395190639","https://openalex.org/W2407793835","https://openalex.org/W2531563875","https://openalex.org/W2623293810","https://openalex.org/W2953006292","https://openalex.org/W2963139738","https://openalex.org/W2963394458","https://openalex.org/W2991116385","https://openalex.org/W4236354166","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2048656453","https://openalex.org/W2041762692","https://openalex.org/W144222265","https://openalex.org/W2567477113","https://openalex.org/W2088116875","https://openalex.org/W2072336782","https://openalex.org/W2051837050","https://openalex.org/W2097224604","https://openalex.org/W2615555727","https://openalex.org/W2104196725"],"abstract_inverted_index":{"In":[0,70,87],"this":[1,28,71],"work,":[2,72],"we":[3,73,113],"address":[4],"the":[5,39,59,91,110,115,122,138],"well-known":[6],"score-based":[7],"Bayesian":[8],"network":[9],"structure":[10],"learning":[11],"problem.":[12,29],"Breadth-first":[13],"branch":[14],"and":[15,120],"bound":[16],"(BFBnB)":[17],"has":[18],"been":[19],"shown":[20],"to":[21],"be":[22],"an":[23,35,43,101],"effective":[24],"approach":[25],"for":[26,68,85,109,136],"solving":[27],"Delayed":[30],"duplicate":[31],"detection":[32],"(DDD)":[33],"is":[34,58,107],"important":[36],"component":[37],"of":[38,61,98,103,124,140],"BFBnB":[40],"algorithm.":[41],"Previously,":[42],"external":[44,126,141],"sorting-based":[45],"technique,":[46,77],"with":[47,78],"complexity":[48,79],"$${\\text":[49,80,92],"{O}}\\left(":[50,81,93],"m":[51,57],"\\log":[52,94],"m\\right)":[53,82,95],"$$":[54,83,96],",":[55,84],"where":[56],"number":[60,139],"nodes":[62],"stored":[63],"in":[64],"memory,":[65],"was":[66],"used":[67],"DDD.":[69,86],"propose":[74],"a":[75,132],"hashing-based":[76],"practice,":[88],"by":[89],"removing":[90],"overhead":[97],"sorting,":[99],"over":[100],"order":[102],"magnitude":[104],"more":[105],"memory":[106,117,127,142],"available":[108],"search.":[111],"Empirically,":[112],"show":[114],"extra":[116],"improves":[118],"locality":[119],"decreases":[121],"amount":[123],"expensive":[125],"operations.":[128],"We":[129],"also":[130],"give":[131],"bin":[133],"packing":[134],"algorithm":[135],"minimizing":[137],"files.":[143]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}