{"id":"https://openalex.org/W2911716162","doi":"https://doi.org/10.1109/bigdata.2018.8622043","title":"Hash-Grams On Many-Cores and Skewed Distributions","display_name":"Hash-Grams On Many-Cores and Skewed Distributions","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2911716162","doi":"https://doi.org/10.1109/bigdata.2018.8622043","mag":"2911716162"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5068036546","display_name":"Edward Raff","orcid":"https://orcid.org/0000-0002-9900-1972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward Raff","raw_affiliation_strings":["Laboratory for Physical Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Physical Sciences","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067728478","display_name":"Mark McLean","orcid":"https://orcid.org/0000-0001-5565-785X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark McLean","raw_affiliation_strings":["Laboratory for Physical Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Physical Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5069,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7543715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"158","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T11269","display_name":"Algorithms and Data Compression","score":1.0,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/hash-function","display_name":"Hash function","score":0.8033304214477539},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.793813169002533},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.6811363697052002},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5892035365104675},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5445225238800049},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5071842670440674},{"id":"https://openalex.org/keywords/skewness","display_name":"Skewness","score":0.4539976716041565},{"id":"https://openalex.org/keywords/double-hashing","display_name":"Double hashing","score":0.444520503282547},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.4354639947414398},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3714066743850708},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3545679450035095},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3520980179309845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18164721131324768},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1142829954624176},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0781029760837555}],"concepts":[{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.8033304214477539},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793813169002533},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6811363697052002},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5892035365104675},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5445225238800049},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5071842670440674},{"id":"https://openalex.org/C122342681","wikidata":"https://www.wikidata.org/wiki/Q330828","display_name":"Skewness","level":2,"score":0.4539976716041565},{"id":"https://openalex.org/C138111711","wikidata":"https://www.wikidata.org/wiki/Q478351","display_name":"Double hashing","level":4,"score":0.444520503282547},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.4354639947414398},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3714066743850708},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3545679450035095},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3520980179309845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18164721131324768},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1142829954624176},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0781029760837555},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622043","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W151938044","https://openalex.org/W1493892051","https://openalex.org/W1553409264","https://openalex.org/W1752655734","https://openalex.org/W1972418517","https://openalex.org/W1974339500","https://openalex.org/W2013092187","https://openalex.org/W2060324268","https://openalex.org/W2070996757","https://openalex.org/W2080234606","https://openalex.org/W2092608522","https://openalex.org/W2102475175","https://openalex.org/W2106163100","https://openalex.org/W2150871235","https://openalex.org/W2295593662","https://openalex.org/W2518866423","https://openalex.org/W2766353929","https://openalex.org/W2894779647","https://openalex.org/W2963437896","https://openalex.org/W4249843299","https://openalex.org/W6629496199","https://openalex.org/W6633322224","https://openalex.org/W6675574014","https://openalex.org/W6726771526"],"related_works":["https://openalex.org/W2069568684","https://openalex.org/W3019245231","https://openalex.org/W1984081611","https://openalex.org/W2376661060","https://openalex.org/W2119251656","https://openalex.org/W2948607823","https://openalex.org/W2171626009","https://openalex.org/W4387251676","https://openalex.org/W1835589799","https://openalex.org/W4385261619"],"abstract_inverted_index":{"When":[0],"using":[1],"n-grams":[2],"for":[3,94],"features,":[4],"it":[5,91],"is":[6,67,101],"often":[7],"the":[8,24,53,65],"case":[9,50],"that":[10],"an":[11],"expedient":[12],"and":[13,85],"effective":[14],"first-pass":[15],"of":[16,37,51,60,87],"feature":[17,41],"selection":[18],"can":[19],"be":[20],"performed":[21],"by":[22],"picking":[23],"top-k":[25],"most":[26],"frequent":[27],"features.":[28],"The":[29],"hash-gram":[30,54,77],"approach":[31],"was":[32],"introduced":[33],"as":[34],"a":[35,48,57,76],"method":[36],"quickly":[38],"performing":[39],"this":[40,44,72],"selection.":[42],"In":[43],"work":[45],"we":[46],"identify":[47],"failure":[49],"parallelizing":[52],"algorithm":[55,78],"to":[56,74],"large":[58],"number":[59,86],"CPU":[61,88],"cores":[62],"P":[63],"when":[64],"data":[66],"highly":[68],"skewed.":[69],"We":[70],"resolve":[71],"issue":[73],"produce":[75],"with":[79],"consistent":[80],"performance":[81],"across":[82],"potential":[83],"skewness-es":[84],"cores,":[89],"making":[90],"practically":[92],"usable":[93],"big-data":[95],"cases":[96],"where":[97],"more":[98],"powerful":[99],"compute":[100],"needed.":[102]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}