{"id":"https://openalex.org/W4406461340","doi":"https://doi.org/10.1109/bigdata62323.2024.10826031","title":"Scalable Sampling for High Utility Patterns","display_name":"Scalable Sampling for High Utility Patterns","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406461340","doi":"https://doi.org/10.1109/bigdata62323.2024.10826031"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10826031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05272675v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102803346","display_name":"Lamine Diop","orcid":"https://orcid.org/0000-0003-4539-2549"},"institutions":[{"id":"https://openalex.org/I4210138808","display_name":"\u00c9cole Pour l'Informatique et les Techniques Avanc\u00e9es","ror":"https://ror.org/04r5ddq29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210138808"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Lamine Diop","raw_affiliation_strings":["Le Kremlin-Bicetre,EPITA Research Laboratory (LRE),Paris,France,FR-94276"],"affiliations":[{"raw_affiliation_string":"Le Kremlin-Bicetre,EPITA Research Laboratory (LRE),Paris,France,FR-94276","institution_ids":["https://openalex.org/I4210138808"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028434928","display_name":"Marc Plantevit","orcid":"https://orcid.org/0000-0003-4636-5753"},"institutions":[{"id":"https://openalex.org/I4210138808","display_name":"\u00c9cole Pour l'Informatique et les Techniques Avanc\u00e9es","ror":"https://ror.org/04r5ddq29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210138808"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marc Plantevit","raw_affiliation_strings":["Le Kremlin-Bicetre,EPITA Research Laboratory (LRE),Paris,France,FR-94276"],"affiliations":[{"raw_affiliation_string":"Le Kremlin-Bicetre,EPITA Research Laboratory (LRE),Paris,France,FR-94276","institution_ids":["https://openalex.org/I4210138808"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102803346"],"corresponding_institution_ids":["https://openalex.org/I4210138808"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41426598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9950000047683716,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9945999979972839,"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":0.7480285167694092},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5711918473243713},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5326359272003174},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14214277267456055},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07616248726844788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480285167694092},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5711918473243713},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5326359272003174},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14214277267456055},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07616248726844788},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10826031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10826031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05272675v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05272675","pdf_url":"https://hal.science/hal-05272675v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"2024 IEEE International Conference on Big Data (BigData), Dec 2024, Washington, France. pp.104-109, ⟨10.1109/BigData62323.2024.10826031⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05272675v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05272675","pdf_url":"https://hal.science/hal-05272675v1/document","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":"2024 IEEE International Conference on Big Data (BigData), Dec 2024, Washington, France. pp.104-109, ⟨10.1109/BigData62323.2024.10826031⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406461340.pdf"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W66155912","https://openalex.org/W80315153","https://openalex.org/W1979462644","https://openalex.org/W2143211346","https://openalex.org/W2340848227","https://openalex.org/W3139497941","https://openalex.org/W3169519622","https://openalex.org/W3201880832","https://openalex.org/W4281294562","https://openalex.org/W4289312207","https://openalex.org/W4320490611","https://openalex.org/W4327814815","https://openalex.org/W4382239259"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2389214306"],"abstract_inverted_index":{"Discovering":[0],"valuable":[1,60],"insights":[2],"from":[3],"data":[4],"through":[5,124],"meaningful":[6],"associations":[7],"is":[8],"a":[9,51,88,136],"crucial":[10],"task.":[11],"However,":[12,66],"it":[13],"becomes":[14],"challenging":[15],"when":[16,73],"trying":[17],"to":[18,34,55,58],"identify":[19],"representative":[20],"patterns":[21,61],"in":[22,80],"quantitative":[23,77,103,151],"databases,":[24],"especially":[25],"with":[26,62,75],"large":[27,76,102],"datasets,":[28],"as":[29,50],"enumeration-based":[30],"strategies":[31],"struggle":[32],"due":[33],"the":[35,114,129,158],"vast":[36],"search":[37],"space":[38,45],"involved.":[39],"To":[40,127],"tackle":[41],"this":[42,84],"challenge,":[43],"output":[44],"sampling":[46,68,93],"methods":[47,69,119],"have":[48],"emerged":[49],"promising":[52],"solution":[53],"thanks":[54],"its":[56,96],"ability":[57],"discover":[59],"reduced":[63],"computational":[64],"overhead.":[65],"existing":[67],"often":[70],"encounter":[71],"limitations":[72],"dealing":[74],"database,":[78],"resulting":[79],"scalability-related":[81],"challenges.":[82],"In":[83],"work,":[85],"we":[86,134],"propose":[87],"novel":[89],"high":[90],"utility":[91],"pattern":[92],"algorithm":[94],"and":[95,120,149],"on-disk":[97],"version":[98],"both":[99,113],"designed":[100],"for":[101,117],"databases":[104,152],"based":[105],"on":[106,147],"two":[107],"original":[108],"theorems.":[109],"Our":[110],"approach":[111,156],"ensures":[112],"interactivity":[115],"required":[116],"user-centered":[118],"strong":[121],"statistical":[122],"guarantees":[123],"random":[125],"sampling.":[126],"demonstrate":[128],"interest":[130],"of":[131],"our":[132,155],"approach,":[133],"present":[135],"compelling":[137],"use":[138],"case":[139],"involving":[140],"archaeological":[141],"knowledge":[142],"graph":[143],"sub-profiles":[144],"discovery.":[145],"Experiments":[146],"semantic":[148],"none-semantic":[150],"show":[153],"that":[154],"outperforms":[157],"state-of-the":[159],"art":[160],"methods.":[161]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}