{"id":"https://openalex.org/W3202505785","doi":"https://doi.org/10.1145/3472456.3472499","title":"Sparker: Efficient Reduction for More Scalable Machine Learning with Spark","display_name":"Sparker: Efficient Reduction for More Scalable Machine Learning with Spark","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3202505785","doi":"https://doi.org/10.1145/3472456.3472499","mag":"3202505785"},"language":"en","primary_location":{"id":"doi:10.1145/3472456.3472499","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472499","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3472456.3472499","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3472456.3472499","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063948705","display_name":"Bowen Yu","orcid":"https://orcid.org/0000-0001-5537-8244"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bowen Yu","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016089490","display_name":"Huanqi Cao","orcid":"https://orcid.org/0000-0002-3870-106X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huanqi Cao","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057212402","display_name":"Tianyi Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyi Shan","raw_affiliation_strings":["University of California San Diego"],"affiliations":[{"raw_affiliation_string":"University of California San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735476","display_name":"Haojie Wang","orcid":"https://orcid.org/0000-0003-4605-148X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Wang","raw_affiliation_strings":["Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011572497","display_name":"Xiongchao Tang","orcid":"https://orcid.org/0000-0002-1692-3964"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiongchao Tang","raw_affiliation_strings":["Sangfor Technologies Inc. and Tsinghua Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"Sangfor Technologies Inc. and Tsinghua Shenzhen International Graduate School","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103141832","display_name":"Wenguang Chen","orcid":"https://orcid.org/0000-0002-4281-1018"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenguang Chen","raw_affiliation_strings":["Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5063948705"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56622732,"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":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9983999729156494,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9983999729156494,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9973000288009644,"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/spark","display_name":"SPARK (programming language)","score":0.9083096981048584},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8610309362411499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7109850645065308},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.7043520212173462},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.578538179397583},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5183299779891968},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.31060880422592163},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.139885812997818},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09160667657852173},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.060785502195358276}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.9083096981048584},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8610309362411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109850645065308},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.7043520212173462},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.578538179397583},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5183299779891968},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.31060880422592163},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.139885812997818},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09160667657852173},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.060785502195358276},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3472456.3472499","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472499","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3472456.3472499","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3472456.3472499","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3472456.3472499","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3472456.3472499","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2082826544","display_name":null,"funder_award_id":"Postdoctoral","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3385202973","display_name":null,"funder_award_id":"U20B2044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6424503130","display_name":null,"funder_award_id":"U20B204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3202505785.pdf","grobid_xml":"https://content.openalex.org/works/W3202505785.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1523128853","https://openalex.org/W1987473040","https://openalex.org/W1991069419","https://openalex.org/W2057332538","https://openalex.org/W2069223570","https://openalex.org/W2114103324","https://openalex.org/W2131613942","https://openalex.org/W2319876296","https://openalex.org/W2542459869","https://openalex.org/W2614375709","https://openalex.org/W2767393956","https://openalex.org/W2783487361","https://openalex.org/W2797862701","https://openalex.org/W2799138232","https://openalex.org/W3087592560","https://openalex.org/W3104493122"],"related_works":["https://openalex.org/W1975949872","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W2905242764","https://openalex.org/W3109411864","https://openalex.org/W4308507533","https://openalex.org/W2407107767","https://openalex.org/W2901787049","https://openalex.org/W4389305770","https://openalex.org/W4401278057"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"applications":[2],"on":[3],"Spark":[4,40],"suffers":[5],"from":[6],"poor":[7],"scalability.":[8],"In":[9],"this":[10],"paper,":[11],"we":[12],"reveal":[13],"that":[14],"the":[15,19,26,78,89],"key":[16],"reasons":[17],"is":[18,23,51],"non-scalable":[20],"reduction,":[21],"which":[22],"restricted":[24],"by":[25,81,96],"non-splittable":[27],"object":[28],"programming":[29],"interface":[30],"in":[31,70],"Spark.":[32],"This":[33],"insight":[34],"guides":[35],"us":[36],"to":[37,53,83,98],"propose":[38],"Sparker,":[39],"with":[41,57,64,101],"Efficient":[42],"Reduction.":[43],"By":[44],"providing":[45],"a":[46,102],"split":[47,55],"aggregation":[48,56,79],"interface,":[49],"Sparker":[50,69,75],"able":[52],"perform":[54],"scalable":[58],"reduction":[59],"while":[60],"being":[61],"backward":[62],"compatible":[63],"existing":[65],"applications.":[66],"We":[67],"implemented":[68],"2,534":[71],"lines":[72],"of":[73,92,105],"code.":[74],"can":[76,87],"improve":[77,88],"performance":[80,91],"up":[82,97],"6.47":[84],"\u00d7":[85,100,107],"and":[86],"end-to-end":[90],"MLlib":[93],"model":[94],"training":[95],"3.69":[99],"geometric":[103],"mean":[104],"1.81":[106],".":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}