{"id":"https://openalex.org/W3136642837","doi":"https://doi.org/10.1109/bigdata50022.2020.9377896","title":"Lineage Checkpoint Approach for Long-lineage Problem in Apache Spark","display_name":"Lineage Checkpoint Approach for Long-lineage Problem in Apache Spark","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3136642837","doi":"https://doi.org/10.1109/bigdata50022.2020.9377896","mag":"3136642837"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5028087500","display_name":"Minhyeok Kweun","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minhyeok Kweun","raw_affiliation_strings":["Samsung Electronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066142084","display_name":"Woo-Yeon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woo-Yeon Lee","raw_affiliation_strings":["Samsung Electronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083776993","display_name":"Goeun Kim","orcid":"https://orcid.org/0000-0002-4937-4092"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Goeun Kim","raw_affiliation_strings":["Samsung Electronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049682044","display_name":"Jisoo Hwang","orcid":"https://orcid.org/0000-0002-1745-7037"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jisoo Hwang","raw_affiliation_strings":["Samsung Electronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081675220","display_name":"Yoonkyong Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoonkyong Lee","raw_affiliation_strings":["Samsung Electronics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Electronics","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8355,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82808858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5733","last_page":"5735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"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":0.9972000122070312,"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/T11719","display_name":"Data Quality and Management","score":0.9972000122070312,"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"}},{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lineage","display_name":"Lineage (genetic)","score":0.8155003786087036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830455303192139},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6373304128646851},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5145673155784607},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.48206478357315063},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19865348935127258},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12895354628562927}],"concepts":[{"id":"https://openalex.org/C2776817793","wikidata":"https://www.wikidata.org/wiki/Q6553369","display_name":"Lineage (genetic)","level":3,"score":0.8155003786087036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830455303192139},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6373304128646851},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5145673155784607},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.48206478357315063},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19865348935127258},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12895354628562927},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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":7,"referenced_works":["https://openalex.org/W1976821017","https://openalex.org/W1982003698","https://openalex.org/W2131975293","https://openalex.org/W2241684952","https://openalex.org/W2295764711","https://openalex.org/W2981937105","https://openalex.org/W6679815717"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2144438995","https://openalex.org/W1577886464","https://openalex.org/W2164896586","https://openalex.org/W1593559483","https://openalex.org/W2108334564","https://openalex.org/W2111125783","https://openalex.org/W2100367016"],"abstract_inverted_index":{"In":[0,78],"distributed":[1],"data":[2,5,16,31,64,89],"processing":[3],"frameworks,":[4],"lineage":[6,23,60,68,74,84],"is":[7],"widely":[8],"used":[9],"to":[10],"achieve":[11],"fault-tolerance":[12],"efficiently.":[13],"However,":[14],"as":[15],"analytics":[17],"apps":[18],"become":[19],"more":[20],"complex,":[21],"long":[22],"incurs":[24],"the":[25,36,52,56,67,72,88],"performance":[26,95],"and":[27,70,96],"reliability":[28],"issues.":[29],"Existing":[30],"checkpoint":[32,85,90],"solutions":[33,91],"can":[34],"alleviate":[35],"problem,":[37],"however":[38],"they":[39],"bring":[40],"new":[41],"types":[42],"of":[43,63,94],"heavy":[44],"inevitable":[45],"overheads":[46],"or":[47],"lack":[48],"fault-tolerance.":[49,97],"To":[50],"overcome":[51],"limitations,":[53],"we":[54,80],"propose":[55],"solution":[57,86],"that":[58,82],"checkpoints":[59],"graph":[61,75],"instead":[62],"itself,":[65],"preserving":[66],"information":[69],"reconciling":[71],"full":[73],"when":[76],"needed.":[77],"evaluations,":[79],"show":[81],"our":[83],"outperforms":[87],"in":[92],"terms":[93]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}