{"id":"https://openalex.org/W2784120864","doi":"https://doi.org/10.1109/bigdata.2017.8257986","title":"Crack random forest for arbitrary large datasets","display_name":"Crack random forest for arbitrary large datasets","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2784120864","doi":"https://doi.org/10.1109/bigdata.2017.8257986","mag":"2784120864"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8257986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8257986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-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/A5045513580","display_name":"Alessandro Lulli","orcid":"https://orcid.org/0000-0003-3881-8900"},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Lulli","raw_affiliation_strings":["DIBRIS-University of Genoa, Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIBRIS-University of Genoa, Genoa, Italy","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045802198","display_name":"Luca Oneto","orcid":"https://orcid.org/0000-0002-8445-395X"},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Oneto","raw_affiliation_strings":["DIBRIS-University of Genoa, Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIBRIS-University of Genoa, Genoa, Italy","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036611143","display_name":"Davide Anguita","orcid":"https://orcid.org/0000-0001-7523-5291"},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Anguita","raw_affiliation_strings":["DIBRIS-University of Genoa, Genoa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DIBRIS-University of Genoa, Genoa, Italy","institution_ids":["https://openalex.org/I83816512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2065,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67115808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"706","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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/T12535","display_name":"Machine Learning and Data Classification","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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9968000054359436,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7213937044143677},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7168053388595581},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6874043941497803},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5543107390403748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5518121719360352},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5294322967529297},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5076121091842651},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4322819709777832},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.415500670671463},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.4111120402812958},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.385028213262558},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3311339020729065},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20462128520011902},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1385599672794342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213937044143677},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7168053388595581},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6874043941497803},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5543107390403748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5518121719360352},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5294322967529297},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5076121091842651},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4322819709777832},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.415500670671463},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4111120402812958},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.385028213262558},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3311339020729065},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20462128520011902},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1385599672794342},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata.2017.8257986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8257986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/962719","is_oa":false,"landing_page_url":"http://hdl.handle.net/11568/962719","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unige.it:11567/914833","is_oa":false,"landing_page_url":"http://hdl.handle.net/11567/914833","pdf_url":null,"source":{"id":"https://openalex.org/S4377196291","display_name":"CINECA IRIS Institutial Research Information System (University of Genoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83816512","host_organization_name":"University of Genoa","host_organization_lineage":["https://openalex.org/I83816512"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W107790154","https://openalex.org/W2006151125","https://openalex.org/W2011876338","https://openalex.org/W2015627422","https://openalex.org/W2040263621","https://openalex.org/W2068696370","https://openalex.org/W2106525823","https://openalex.org/W2117897510","https://openalex.org/W2125283600","https://openalex.org/W2125621954","https://openalex.org/W2125816831","https://openalex.org/W2132549764","https://openalex.org/W2146068631","https://openalex.org/W2148603752","https://openalex.org/W2162772535","https://openalex.org/W2173213060","https://openalex.org/W2174668940","https://openalex.org/W2189465200","https://openalex.org/W2193121729","https://openalex.org/W2414869151","https://openalex.org/W2490023472","https://openalex.org/W2517850251","https://openalex.org/W2544661862","https://openalex.org/W2557956978","https://openalex.org/W2565979531","https://openalex.org/W2567617232","https://openalex.org/W2911964244","https://openalex.org/W2998768810","https://openalex.org/W3010411193","https://openalex.org/W6687322159","https://openalex.org/W6698146022","https://openalex.org/W6722680694","https://openalex.org/W6726337007","https://openalex.org/W6731552020"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W4389724018","https://openalex.org/W4318719684","https://openalex.org/W3183136280","https://openalex.org/W4318559728","https://openalex.org/W2775233965","https://openalex.org/W4360995913","https://openalex.org/W4386295066"],"abstract_inverted_index":{"Random":[0,118],"Forests":[1],"(RF)":[2],"of":[3,25,81,130,147,163,181],"tree":[4],"classifiers":[5],"are":[6,33],"a":[7,120],"state-of-the-art":[8,45],"method":[9],"for":[10],"classification":[11,187],"purposes.":[12],"RF":[13,55,76],"show":[14,51],"limited":[15],"hyperparameter":[16],"sensitivity,":[17],"have":[18],"high":[19],"numerical":[20,28],"robustness,":[21],"possess":[22],"native":[23],"capacity":[24],"dealing":[26],"with":[27,41],"and":[29,32,93,100,142,160,165,183,186],"categorical":[30],"features,":[31],"quite":[34,121],"effective":[35],"in":[36,56,110,179],"many":[37],"real":[38,169],"world":[39,170],"problems":[40],"respect":[42],"to":[43,53,58,61,86,89,106],"other":[44],"techniques.":[46],"In":[47,68],"this":[48],"work":[49],"we":[50,70],"how":[52],"crack":[54],"order":[57],"be":[59],"able":[60,105],"train":[62],"them":[63],"on":[64,96,167],"arbitrary":[65],"large":[66],"datasets.":[67,171],"particular,":[69],"extend":[71],"ReForeSt,":[72],"an":[73,136],"Apache":[74],"Spark-based":[75],"implementation.":[77],"The":[78,113],"new":[79,114],"version":[80],"ReForeSt":[82,115,141,164,175,189],"computation":[83,95],"automatically":[84,101],"adapts":[85],"two":[87],"methodologies":[88],"distribute":[90],"the":[91,94,97,103,108,128,131,148,158,161],"data":[92],"available":[98,192],"machines":[99],"chooses":[102],"one":[104],"provide":[107],"result":[109],"less":[111],"time.":[112],"also":[116],"supports":[117],"Rotations,":[119],"recent":[122],"randomization":[123],"technique":[124],"which":[125],"can":[126],"bust":[127],"accuracy":[129],"original":[132],"RF.":[133],"We":[134,156],"perform":[135],"extensive":[137],"experimental":[138],"evaluation":[139],"between":[140],"MLlib":[143,166,177],"by":[144],"taking":[145],"advantage":[146],"Google":[149],"Cloud":[150],"Platform":[151],"<sup":[152,195],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[153,196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[154],".":[155,198],"test":[157],"performances":[159],"scalability":[162],"several":[168],"Results":[172],"confirm":[173],"that":[174],"outperforms":[176],"both":[178],"terms":[180],"memory":[182],"computational":[184],"efficiency,":[185],"performances.":[188],"is":[190],"publicly":[191],"via":[193],"GitHub":[194],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[197]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}