{"id":"https://openalex.org/W2896688807","doi":"https://doi.org/10.1145/3269206.3271752","title":"A Scalable Algorithm for Higher-order Features Generation using MinHash","display_name":"A Scalable Algorithm for Higher-order Features Generation using MinHash","publication_year":2018,"publication_date":"2018-10-17","ids":{"openalex":"https://openalex.org/W2896688807","doi":"https://doi.org/10.1145/3269206.3271752","mag":"2896688807"},"language":"en","primary_location":{"id":"doi:10.1145/3269206.3271752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3269206.3271752","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3269206.3271752","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3269206.3271752","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108998577","display_name":"A Pooja","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pooja A","raw_affiliation_strings":["Amazon, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007940093","display_name":"N. V. Nair","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naveen Nair","raw_affiliation_strings":["Amazon Development Centre, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Development Centre, Seattle, WA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111717871","display_name":"Rajeev Rastogi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajeev Rastogi","raw_affiliation_strings":["Amazon Development Centre, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Development Centre, Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2075,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50050623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1213","last_page":"1222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9965999722480774,"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":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8911926746368408},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8427689075469971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8280781507492065},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7657228708267212},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7130106687545776},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5506552457809448},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5429224371910095},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42930251359939575},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4225267469882965},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39377766847610474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37306779623031616},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11061084270477295}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8911926746368408},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8427689075469971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280781507492065},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7657228708267212},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7130106687545776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5506552457809448},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5429224371910095},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42930251359939575},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4225267469882965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39377766847610474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37306779623031616},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11061084270477295},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3269206.3271752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3269206.3271752","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3269206.3271752","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3269206.3271752","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3269206.3271752","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3269206.3271752","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2896688807.pdf","grobid_xml":"https://content.openalex.org/works/W2896688807.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1661871015","https://openalex.org/W1982414171","https://openalex.org/W2043772506","https://openalex.org/W2046945713","https://openalex.org/W2048779798","https://openalex.org/W2055906546","https://openalex.org/W2089497633","https://openalex.org/W2097865464","https://openalex.org/W2109293916","https://openalex.org/W2132069633","https://openalex.org/W2144902422","https://openalex.org/W2150307973","https://openalex.org/W2152565070","https://openalex.org/W2154053567","https://openalex.org/W2155925556","https://openalex.org/W2156504490","https://openalex.org/W2162833766","https://openalex.org/W2165580920","https://openalex.org/W2169446650","https://openalex.org/W2279057335","https://openalex.org/W2517540742","https://openalex.org/W2560674852","https://openalex.org/W2998216295","https://openalex.org/W3097993951","https://openalex.org/W3120740533","https://openalex.org/W4285719527","https://openalex.org/W4289236186"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W3170260665","https://openalex.org/W3137434606","https://openalex.org/W4372263373"],"abstract_inverted_index":{"Linear":[0],"models":[1,21],"have":[2],"been":[3],"widely":[4],"used":[5],"in":[6,30,156,194],"the":[7,32,50,70,79,142,188],"industry":[8],"for":[9,83,114],"their":[10,36,138],"low":[11],"computation":[12],"time,":[13],"small":[14],"memory":[15,91,146],"footprint":[16],"and":[17,118,134,145,161],"interpretability.":[18],"However,":[19],"linear":[20],"are":[22,76],"not":[23,180],"capable":[24],"of":[25,49,62,78,112,125,158],"leveraging":[26],"non-linear":[27],"feature":[28,191],"interactions":[29,192],"predicting":[31],"target.":[33],"This":[34,85],"limits":[35],"performance.":[37,197],"A":[38],"classical":[39],"approach":[40,178],"to":[41,46,57,104,127,136,164,186],"overcome":[42],"this":[43,94],"limitation":[44],"is":[45,81,86,153,179],"use":[47,111,122],"combinations":[48],"original":[51],"features,":[52,56],"referred":[53],"as":[54],"higher-order":[55,63,107,132],"capture":[58],"non-linearity.":[59],"The":[60],"number":[61],"features":[64,126,133],"can":[65],"be":[66],"very":[67],"large.":[68],"Selecting":[69],"informative":[71,106],"ones":[72],"among":[73],"them":[74],"that":[75,150,175],"predictive":[77],"target":[80,135],"essential":[82],"scalability.":[84],"computationally":[87],"expensive,":[88],"requiring":[89],"large":[90],"footprint.":[92],"In":[93],"paper,":[95],"we":[96,121,148],"propose":[97],"a":[98],"novel":[99],"scalable":[100],"MinHash":[101,113,123],"based":[102],"scheme":[103],"select":[105],"features.":[108],"Unlike":[109],"typical":[110],"near-duplicate":[115],"entity":[116],"detection":[117],"association-rule":[119],"mining,":[120],"signature":[124],"approximate":[128],"mutual":[129],"information":[130],"between":[131],"enable":[137],"selection.":[139],"By":[140],"analyzing":[141],"running":[143,159],"time":[144,160],"requirements,":[147],"show":[149],"our":[151,176],"proposal":[152],"highly":[154],"efficient":[155],"terms":[157],"storage":[162],"compared":[163],"existing":[165],"alternatives.":[166],"We":[167],"demonstrate":[168],"through":[169],"experiments":[170],"on":[171],"multiple":[172],"benchmark":[173],"datasets":[174],"proposed":[177],"only":[181],"scalable,":[182],"but":[183],"also":[184],"able":[185],"identify":[187],"most":[189],"important":[190],"resulting":[193],"improved":[195],"model":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}