{"id":"https://openalex.org/W2962936736","doi":"https://doi.org/10.1145/3337821.3337823","title":"Lightweight Fault Tolerance in Pregel-Like Systems","display_name":"Lightweight Fault Tolerance in Pregel-Like Systems","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2962936736","doi":"https://doi.org/10.1145/3337821.3337823","mag":"2962936736"},"language":"en","primary_location":{"id":"doi:10.1145/3337821.3337823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3337821.3337823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3337821.3337823","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th 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/10.1145/3337821.3337823","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070582509","display_name":"Da Yan","orcid":"https://orcid.org/0000-0002-4653-0408"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Da Yan","raw_affiliation_strings":["University of Alabama at Birmingham"],"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016082884","display_name":"James Cheng","orcid":"https://orcid.org/0000-0001-6313-6288"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"James Cheng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101653376","display_name":"Hongzhi Chen","orcid":"https://orcid.org/0000-0002-0085-3463"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Chen","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044528555","display_name":"Cheng Long","orcid":"https://orcid.org/0000-0001-6806-8405"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Cheng Long","raw_affiliation_strings":["Nanyang Technological University"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084732782","display_name":"Purushotham Bangalore","orcid":"https://orcid.org/0000-0002-1098-9997"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Purushotham Bangalore","raw_affiliation_strings":["University of Alabama at Birmingham"],"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham","institution_ids":["https://openalex.org/I32389192"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070582509"],"corresponding_institution_ids":["https://openalex.org/I32389192"],"apc_list":null,"apc_paid":null,"fwci":1.2972,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82271595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9988999962806702,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987000226974487,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.787053108215332},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7865855693817139},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6622008681297302},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48108598589897156},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.45646536350250244},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4531136751174927},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4499009847640991},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4470750689506531},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4339498281478882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787053108215332},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7865855693817139},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6622008681297302},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48108598589897156},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.45646536350250244},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4531136751174927},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4499009847640991},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4470750689506531},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4339498281478882},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3337821.3337823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3337821.3337823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3337821.3337823","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3337821.3337823","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3337821.3337823","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3337821.3337823","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1229750795","display_name":null,"funder_award_id":"OAC-1755464, DGE-1723250 and CCF-1562306","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2566658944","display_name":"SaTC: EDU: Captivology-Stimuli-based Learning (CAPITAL) of Big Data Security (BigSec): Towards a Science/Engineering, Career-Oriented Training","funder_award_id":"1723250","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G343156164","display_name":null,"funder_award_id":"India","funder_id":"https://openalex.org/F4320322724","funder_display_name":"Ministry of Education, India"},{"id":"https://openalex.org/G3592454421","display_name":"SHF: Medium: Collaborative Research: Next-Generation Message Passing for Parallel Programming: Resiliency, Time-to-Solution, Performance-Portability, Scalability, and QoS","funder_award_id":"1562306","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4551403911","display_name":null,"funder_award_id":"6904945","funder_id":"https://openalex.org/F4320326427","funder_display_name":"Innovation and Technology Fund"},{"id":"https://openalex.org/G5106231682","display_name":null,"funder_award_id":"CCF-1562306","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5927600624","display_name":null,"funder_award_id":"Scheme for Promotion of Academic and Research Collaboration (SPARC)","funder_id":"https://openalex.org/F4320322724","funder_display_name":"Ministry of Education, India"},{"id":"https://openalex.org/G6489494027","display_name":"CRII: OAC: Scalable Cyberinfrastructure for Big Graph and Matrix/Tensor Analytics","funder_award_id":"1755464","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7040846913","display_name":null,"funder_award_id":"SPARC","funder_id":"https://openalex.org/F4320322724","funder_display_name":"Ministry of Education, India"},{"id":"https://openalex.org/G950846825","display_name":null,"funder_award_id":"14222816","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"},{"id":"https://openalex.org/F4320326427","display_name":"Innovation and Technology Fund","ror":null},{"id":"https://openalex.org/F4320330412","display_name":"Scheme for Promotion of Academic and Research Collaboration","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2962936736.pdf","grobid_xml":"https://content.openalex.org/works/W2962936736.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W107790154","https://openalex.org/W1448681276","https://openalex.org/W1501254937","https://openalex.org/W2010347674","https://openalex.org/W2085426754","https://openalex.org/W2100970777","https://openalex.org/W2170616854","https://openalex.org/W2219156867","https://openalex.org/W2263854845","https://openalex.org/W2266486761","https://openalex.org/W2296407087","https://openalex.org/W2588458088","https://openalex.org/W2730779250","https://openalex.org/W2949679549"],"related_works":["https://openalex.org/W2971479921","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W2101077206","https://openalex.org/W2157727563","https://openalex.org/W2470343202","https://openalex.org/W1978919910","https://openalex.org/W1488443159","https://openalex.org/W1504391205"],"abstract_inverted_index":{"Pregel-like":[0,17,58,140],"systems":[1,18],"are":[2,51,83,126],"popular":[3],"for":[4,25,81],"iterative":[5],"graph":[6],"processing":[7],"thanks":[8],"to":[9,74,128],"their":[10],"user-friendly":[11],"vertex-centric":[12],"programming":[13],"model.":[14],"However,":[15],"existing":[16],"only":[19],"adopt":[20],"a":[21,30,63,104,139],"na\u00efve":[22],"checkpointing":[23,66,135],"approach":[24,109],"fault":[26,48],"tolerance,":[27],"which":[28,69],"saves":[29],"large":[31],"amount":[32],"of":[33,38,57,101,133],"data":[34,72,79],"about":[35],"the":[36,43,55,71,87,131],"state":[37],"computation":[39],"and":[40,77,98,136],"significantly":[41,129],"degrades":[42],"failure-free":[44],"execution":[45],"performance.":[46],"Advanced":[47],"tolerance/recovery":[49],"techniques":[50,125],"left":[52],"unexplored":[53],"in":[54,93,96,138],"context":[56],"systems.":[59],"This":[60,90],"paper":[61],"proposes":[62],"non-invasive":[64],"lightweight":[65],"(LWCP)":[67],"scheme":[68],"minimizes":[70],"saved":[73,88],"each":[75],"checkpoint,":[76],"additional":[78],"required":[80],"recovery":[82,108,114,137],"generated":[84],"online":[85],"from":[86],"data.":[89],"improvement":[91],"results":[92],"10x":[94],"speedup":[95],"checkpointing,":[97],"an":[99],"integration":[100],"it":[102],"with":[103],"recently":[105],"proposed":[106,123],"log-based":[107],"can":[110],"further":[111],"speed":[112],"up":[113],"when":[115],"failure":[116],"occurs.":[117],"Extensive":[118],"experiments":[119],"verified":[120],"that":[121],"our":[122],"LWCP":[124],"able":[127],"improve":[130],"performance":[132],"both":[134],"system.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-10-10T00:00:00"}
