{"id":"https://openalex.org/W2182237911","doi":"https://doi.org/10.14778/2733004.2733044","title":"A partitioning framework for aggressive data skipping","display_name":"A partitioning framework for aggressive data skipping","publication_year":2014,"publication_date":"2014-08-01","ids":{"openalex":"https://openalex.org/W2182237911","doi":"https://doi.org/10.14778/2733004.2733044","mag":"2182237911"},"language":"en","primary_location":{"id":"doi:10.14778/2733004.2733044","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2733004.2733044","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5087740768","display_name":"Liwen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liwen Sun","raw_affiliation_strings":["AMPLab, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"AMPLab, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018480426","display_name":"Sanjay Krishnan","orcid":"https://orcid.org/0000-0001-6968-4090"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Krishnan","raw_affiliation_strings":["AMPLab, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"AMPLab, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000259060","display_name":"Reynold Xin","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reynold S. Xin","raw_affiliation_strings":["AMPLab, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"AMPLab, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102019638","display_name":"Michael J. Franklin","orcid":"https://orcid.org/0000-0003-3332-8574"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael J. Franklin","raw_affiliation_strings":["AMPLab, UC Berkeley"],"affiliations":[{"raw_affiliation_string":"AMPLab, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5087740768"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.5888,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.70108913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"7","issue":"13","first_page":"1617","last_page":"1620"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/tuple","display_name":"Tuple","score":0.8595374822616577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7897684574127197},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.7793383598327637},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6704431176185608},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6304147243499756},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6001421213150024},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5085190534591675},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4901159703731537},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47784659266471863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18715327978134155},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10776618123054504}],"concepts":[{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8595374822616577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897684574127197},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.7793383598327637},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6704431176185608},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6304147243499756},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6001421213150024},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5085190534591675},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4901159703731537},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47784659266471863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18715327978134155},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10776618123054504},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/2733004.2733044","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2733004.2733044","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.642.3699","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.642.3699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/vol7/p1617-sun.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1967601791","https://openalex.org/W1981988185","https://openalex.org/W2003580796","https://openalex.org/W2131975293","https://openalex.org/W2139072600"],"related_works":["https://openalex.org/W2110553125","https://openalex.org/W3010198599","https://openalex.org/W2598498736","https://openalex.org/W2075832457","https://openalex.org/W2366051640","https://openalex.org/W2614500124","https://openalex.org/W2991126413","https://openalex.org/W2103652998","https://openalex.org/W3043816525","https://openalex.org/W2250140425"],"abstract_inverted_index":{"We":[0],"propose":[1],"to":[2,23,26,84,94,119],"demonstrate":[3],"a":[4,46,57,65,71,81,108],"fine-grained":[5],"partitioning":[6,117],"framework":[7,34],"that":[8,103],"reorganizes":[9],"the":[10,86,91,96],"data":[11,17,30,54,68,98,122],"tuples":[12,69],"into":[13],"small":[14],"blocks":[15],"at":[16],"loading":[18],"time.":[19],"The":[20,32],"goal":[21],"is":[22],"enable":[24],"queries":[25],"maximally":[27],"skip":[28],"scanning":[29],"blocks.":[31],"partition":[33,85],"consists":[35],"of":[36,67,73],"four":[37],"steps:":[38],"(1)":[39],"workload":[40],"analysis,":[41],"which":[42,51,62,79],"extracts":[43],"features":[44],"from":[45],"query":[47,110],"workload,":[48],"(2)":[49],"augmentation,":[50],"augments":[52],"each":[53],"tuple":[55],"with":[56],"feature":[58,74,87],"vector,":[59],"(3)":[60],"reduce,":[61],"succinctly":[63],"represents":[64],"set":[66,72],"using":[70],"vectors,":[75],"and":[76,89],"(4)":[77],"partitioning,":[78],"performs":[80],"clustering":[82,92],"algorithm":[83],"vectors":[88],"uses":[90],"result":[93,106],"guide":[95],"actual":[97],"partitioning.":[99],"Our":[100],"experiments":[101],"show":[102],"our":[104],"techniques":[105],"in":[107],"3-7x":[109],"response":[111],"time":[112],"improvement":[113],"over":[114],"traditional":[115],"range":[116],"due":[118],"more":[120],"effective":[121],"skipping.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}