{"id":"https://openalex.org/W4393220152","doi":"https://doi.org/10.1186/s40537-024-00906-9","title":"The role of classifiers and data complexity in learned Bloom filters: insights and recommendations","display_name":"The role of classifiers and data complexity in learned Bloom filters: insights and recommendations","publication_year":2024,"publication_date":"2024-03-27","ids":{"openalex":"https://openalex.org/W4393220152","doi":"https://doi.org/10.1186/s40537-024-00906-9"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-024-00906-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00906-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00906-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00906-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005837237","display_name":"Dario Malchiodi","orcid":"https://orcid.org/0000-0002-7574-697X"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]},{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]}],"countries":["IT","US"],"is_corresponding":true,"raw_author_name":"Dario Malchiodi","raw_affiliation_strings":["CINI National Laboratory of Artificial Intelligence and Intelligent Systems (AIIS), University of Rome, 00185, Rome, Italy","Department of Computer Science, Universit\u00e0 degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0002-7574-697X","affiliations":[{"raw_affiliation_string":"CINI National Laboratory of Artificial Intelligence and Intelligent Systems (AIIS), University of Rome, 00185, Rome, Italy","institution_ids":["https://openalex.org/I4210105785"]},{"raw_affiliation_string":"Department of Computer Science, Universit\u00e0 degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000175310","display_name":"Davide Raimondi","orcid":"https://orcid.org/0000-0001-8171-8302"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Raimondi","raw_affiliation_strings":["Department of Computer Science, Universit\u00e0 degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universit\u00e0 degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001296699","display_name":"Giacomo Fumagalli","orcid":"https://orcid.org/0000-0002-2068-9293"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giacomo Fumagalli","raw_affiliation_strings":["Department of Computer Science, Universit\u00e0 degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universit\u00e0 degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078881318","display_name":"Raffaele Giancarlo","orcid":"https://orcid.org/0000-0002-6286-8871"},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Raffaele Giancarlo","raw_affiliation_strings":["Department of Mathematics and CS, University of Palermo, Via Archirafi 34, 90123, Palermo, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics and CS, University of Palermo, Via Archirafi 34, 90123, Palermo, Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080851861","display_name":"Marco Frasca","orcid":"https://orcid.org/0000-0002-0163-0659"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Frasca","raw_affiliation_strings":["Department of Computer Science, Universit\u00e0 degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universit\u00e0 degli Studi di Milano, Via Celoria 18, 20133, Milan, Italy","institution_ids":["https://openalex.org/I189158943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005837237"],"corresponding_institution_ids":["https://openalex.org/I189158943","https://openalex.org/I4210105785"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1923,"currency":"EUR","value_usd":2073},"fwci":0.6294,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71604694,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"11","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9977999925613403,"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/T11478","display_name":"Caching and Content Delivery","score":0.9929999709129333,"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/bloom-filter","display_name":"Bloom filter","score":0.8365261554718018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7706853151321411},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.7328585386276245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5084378123283386},{"id":"https://openalex.org/keywords/bloom","display_name":"Bloom","score":0.48616406321525574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4373611509799957},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.427237331867218},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33510154485702515},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10453441739082336}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.8365261554718018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7706853151321411},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.7328585386276245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5084378123283386},{"id":"https://openalex.org/C155567681","wikidata":"https://www.wikidata.org/wiki/Q2987425","display_name":"Bloom","level":2,"score":0.48616406321525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4373611509799957},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.427237331867218},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33510154485702515},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10453441739082336},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s40537-024-00906-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00906-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00906-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:air.unimi.it:2434/1050422","is_oa":true,"landing_page_url":"https://hdl.handle.net/2434/1050422","pdf_url":"https://air.unimi.it/bitstream/2434/1050422/2/s40537-024-00906-9%20%281%29.pdf","source":{"id":"https://openalex.org/S4306400516","display_name":"Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189158943","host_organization_name":"University of Milan","host_organization_lineage":["https://openalex.org/I189158943"],"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":"","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.unipa.it:10447/632153","is_oa":true,"landing_page_url":"https://hdl.handle.net/10447/632153","pdf_url":"https://iris.unipa.it/bitstream/10447/632153/2/The%20role%20of%20classifers%20and%20data.pdf","source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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/article"},{"id":"pmh:oai:doaj.org/article:dcca9510937d4ec59a72413c66db0a69","is_oa":true,"landing_page_url":"https://doaj.org/article/dcca9510937d4ec59a72413c66db0a69","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 11, Iss 1, Pp 1-26 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-024-00906-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00906-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00906-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311030","display_name":"Istituto Nazionale di Alta Matematica \"Francesco Severi\"","ror":"https://ror.org/01vx64p53"},{"id":"https://openalex.org/F4320313475","display_name":"Universit\u00e0 degli Studi di Milano","ror":"https://ror.org/00wjc7c48"},{"id":"https://openalex.org/F4320331528","display_name":"Ministero dell'Universit\u00e0 e della Ricerca","ror":null},{"id":"https://openalex.org/F4320334079","display_name":"Gruppo Nazionale per il Calcolo Scientifico","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393220152.pdf"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1594031697","https://openalex.org/W1976594146","https://openalex.org/W1981420413","https://openalex.org/W1985623009","https://openalex.org/W1993284846","https://openalex.org/W2004710424","https://openalex.org/W2005228765","https://openalex.org/W2012035409","https://openalex.org/W2038128936","https://openalex.org/W2052207834","https://openalex.org/W2064803799","https://openalex.org/W2065358485","https://openalex.org/W2078772598","https://openalex.org/W2097160089","https://openalex.org/W2118978333","https://openalex.org/W2119168155","https://openalex.org/W2121873871","https://openalex.org/W2122379760","https://openalex.org/W2123845384","https://openalex.org/W2163584430","https://openalex.org/W2266239166","https://openalex.org/W2800394774","https://openalex.org/W2903950532","https://openalex.org/W2911964244","https://openalex.org/W2962771342","https://openalex.org/W2964199361","https://openalex.org/W2973136425","https://openalex.org/W2979531022","https://openalex.org/W2990138404","https://openalex.org/W3018149777","https://openalex.org/W3018162653","https://openalex.org/W3030149280","https://openalex.org/W3033065823","https://openalex.org/W3082379938","https://openalex.org/W3093722121","https://openalex.org/W3096737792","https://openalex.org/W3103672149","https://openalex.org/W3118971041","https://openalex.org/W3121516856","https://openalex.org/W3128253198","https://openalex.org/W3137108924","https://openalex.org/W3158158480","https://openalex.org/W3158552329","https://openalex.org/W3175744197","https://openalex.org/W4200634901","https://openalex.org/W4205687621","https://openalex.org/W4214910385","https://openalex.org/W4229602251","https://openalex.org/W4294755440","https://openalex.org/W4300601563","https://openalex.org/W4310147199","https://openalex.org/W4323313010","https://openalex.org/W4361277572","https://openalex.org/W4379528647","https://openalex.org/W4384303994","https://openalex.org/W4385071102","https://openalex.org/W6776565550","https://openalex.org/W6843735874","https://openalex.org/W7014191107"],"related_works":["https://openalex.org/W2086572746","https://openalex.org/W2604468458","https://openalex.org/W2157216338","https://openalex.org/W1662107788","https://openalex.org/W121740227","https://openalex.org/W4293466821","https://openalex.org/W2051000928","https://openalex.org/W2785871494","https://openalex.org/W4298105090","https://openalex.org/W2789524206"],"abstract_inverted_index":{"Abstract":[0],"Bloom":[1,45,111,156,225],"filters,":[2],"since":[3],"their":[4,116],"introduction":[5],"over":[6],"50":[7],"years":[8],"ago,":[9],"have":[10,33,202,245],"become":[11],"a":[12,146,189],"pillar":[13],"to":[14,66,149,161,244,251],"handle":[15],"membership":[16],"queries":[17],"in":[18,24,62,64,120,153,212,220],"small":[19],"space,":[20],"with":[21,37,214],"relevant":[22],"application":[23],"Big":[25],"Data":[26],"Mining":[27],"and":[28,77,108,126,215,254],"Stream":[29],"Processing.":[30],"Further":[31,159],"improvements":[32],"been":[34],"recently":[35],"proposed":[36,137],"the":[38,53,67,80,84,91,133,136,150,162,165,168,177,180,192,198,221,235,246],"use":[39],"of":[40,57,69,71,83,90,135,164,167,172,197,234,237,249],"Machine":[41],"Learning":[42],"techniques:":[43],"learned":[44,110,155],"filters.":[46,157],"Those":[47],"latter":[48],"make":[49],"considerably":[50],"more":[51],"complicated":[52],"proper":[54],"parameter":[55],"setting":[56],"this":[58,88,209,238],"multi-criteria":[59,118],"data":[60,127,252],"structure,":[61],"particular":[63,121],"regard":[65],"choice":[68,125],"one":[70,233],"its":[72],"key":[73],"components":[74],"(the":[75],"classifier)":[76],"accounting":[78],"for":[79,105,115,191],"classification":[81,128],"complexity":[82,253],"input":[85],"dataset.":[86],"Given":[87],"State":[89,166],"Art,":[92],"our":[93,141],"contributions":[94,160],"are":[95,171,176],"as":[96,188,231],"follows.":[97],"(1)":[98],"A":[99],"novel":[100],"methodology,":[101],"supported":[102],"by":[103],"software,":[104],"designing,":[106],"analyzing":[107],"implementing":[109],"filters":[112],"that":[113,170],"account":[114],"own":[117],"nature,":[119],"concerning":[122],"classifier":[123,181,255],"type":[124],"complexity.":[129],"Extensive":[130],"experiments":[131],"show":[132],"validity":[134],"methodology":[138],"and,":[139],"being":[140,232],"software":[142],"public,":[143],"we":[144,201],"offer":[145,206],"valid":[147],"tool":[148],"practitioners":[151],"interested":[152],"using":[154],"(2)":[158],"advancement":[163],"Art":[169],"great":[173],"practical":[174],"relevance":[175],"following:":[178],"(a)":[179],"inference":[182],"time":[183],"should":[184],"not":[185],"be":[186],"taken":[187],"proxy":[190],"filter":[193],"reject":[194],"time;":[195],"(b)":[196],"many":[199],"classifiers":[200],"considered,":[203],"only":[204],"two":[205],"good":[207],"performance;":[208],"result":[210],"is":[211,228,240],"agreement":[213],"further":[216,241],"strengthens":[217],"early":[218],"findings":[219],"literature;":[222],"(c)":[223],"Sandwiched":[224],"filter,":[226],"which":[227],"already":[229],"known":[230],"references":[236],"area,":[239],"shown":[242],"here":[243],"remarkable":[247],"property":[248],"robustness":[250],"performance":[256],"variability.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}