{"id":"https://openalex.org/W2920513979","doi":"https://doi.org/10.1145/3290420.3290460","title":"Efficient spark analysis on incremental datasets","display_name":"Efficient spark analysis on incremental datasets","publication_year":2018,"publication_date":"2018-11-02","ids":{"openalex":"https://openalex.org/W2920513979","doi":"https://doi.org/10.1145/3290420.3290460","mag":"2920513979"},"language":"en","primary_location":{"id":"doi:10.1145/3290420.3290460","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3290420.3290460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Wei Sheng","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Sheng","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089034482","display_name":"Zhao Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Cao","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012723143","display_name":"Dacheng Qu","orcid":"https://orcid.org/0000-0003-2495-7977"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dacheng Qu","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27019413,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976999759674072,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/spark","display_name":"SPARK (programming language)","score":0.8482357263565063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8313169479370117},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5389747023582458},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5322413444519043},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.5101156830787659},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.49660545587539673},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.44414541125297546},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.43673112988471985},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4320870339870453},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.42645666003227234},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27234745025634766},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11624118685722351},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10508424043655396}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8482357263565063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313169479370117},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5389747023582458},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5322413444519043},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.5101156830787659},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.49660545587539673},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.44414541125297546},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.43673112988471985},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4320870339870453},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.42645666003227234},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27234745025634766},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11624118685722351},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10508424043655396},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3290420.3290460","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3290420.3290460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th International Conference on Communication and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W55296414","https://openalex.org/W153732537","https://openalex.org/W410850256","https://openalex.org/W1966764836","https://openalex.org/W1976821017","https://openalex.org/W1981420413","https://openalex.org/W1982003698","https://openalex.org/W2010929544","https://openalex.org/W2026205964","https://openalex.org/W2038412523","https://openalex.org/W2096092966","https://openalex.org/W2109097687","https://openalex.org/W2119565742","https://openalex.org/W2144002928","https://openalex.org/W2173213060","https://openalex.org/W2245432647","https://openalex.org/W2963288913","https://openalex.org/W6614148910"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"Distributed":[0],"analysis":[1,13],"platform":[2],"such":[3],"as":[4],"Spark":[5,86],"provides":[6],"an":[7,50,152],"unprecedented":[8],"capacity":[9],"on":[10,32,53],"big":[11],"data":[12,71,109],"processing,":[14],"especially,":[15],"for":[16,85,104,123],"Extract-Transform-Load":[17],"(ETL),":[18],"which":[19,82],"has":[20],"won":[21],"the":[22,88,145,176,182],"wide":[23],"recognition":[24],"by":[25,111,133],"academia":[26],"and":[27,76,169,181],"industry.":[28],"The":[29],"performance":[30,130],"based":[31],"Spark,":[33],"however,":[34],"comes":[35],"from":[36,107,160],"immutable":[37],"datasets":[38,60,106],"losing":[39],"flexibility":[40],"of":[41,147,178,184],"mutable":[42],"ones":[43],"with":[44],"trivial":[45],"changes.":[46],"Therefore,":[47],"there":[48],"is":[49,83,93,141],"unmet":[51],"demand":[52],"how":[54],"to":[55,79,115,127,143],"efficiently":[56],"integrate":[57],"distributed":[58,90],"dynamical":[59],"between":[61,166],"two":[62],"or":[63,68,155],"more":[64],"autonomous":[65],"computer":[66],"systems":[67],"servers.":[69],"Traditional":[70],"synchronization":[72],"solutions":[73],"detect":[74],"changes":[75,150],"apply":[77],"them":[78],"target":[80],"datasets,":[81],"impossible":[84],"since":[87],"resilient":[89],"dataset":[91],"(RDD)":[92],"invariant":[94],"in":[95],"nature.":[96],"In":[97],"this":[98],"paper,":[99],"we":[100],"design":[101],"a":[102,138,157,164],"paradigm":[103],"integrating":[105],"several":[108],"repositories":[110],"extending":[112],"RDD":[113,125,154,159],"mechanism":[114],"enable":[116],"incremental":[117,167,179],"processing.":[118],"We":[119],"use":[120],"appended":[121],"logs":[122],"each":[124],"component":[126],"avoid":[128],"serious":[129],"degradation":[131],"caused":[132],"re-fetching":[134,170],"full":[135],"dataset.":[136],"Furthermore,":[137],"cost":[139,146,186],"model":[140],"proposed":[142],"evaluate":[144],"merging":[148],"these":[149],"into":[151],"existing":[153],"forming":[156],"new":[158],"scratch,":[161],"providing":[162],"us":[163],"balance":[165],"processing":[168,180],"explicitly.":[171],"Our":[172],"experimental":[173],"results":[174],"demonstrate":[175],"necessity":[177],"effectiveness":[183],"our":[185],"model.":[187]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
