{"id":"https://openalex.org/W4388581089","doi":"https://doi.org/10.1145/3624062.3626080","title":"Elastic deep learning through resilient collective operations","display_name":"Elastic deep learning through resilient collective operations","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388581089","doi":"https://doi.org/10.1145/3624062.3626080"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3626080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3626080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3626080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3626080","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023743368","display_name":"Jiali Li","orcid":"https://orcid.org/0000-0001-7929-8484"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiali Li","raw_affiliation_strings":["the University of Tennessee, Knoxville, United States of America","The University of Tennessee [Knoxville] (Knoxville, Tennessee 37996 - United States)"],"raw_orcid":"https://orcid.org/0000-0001-7929-8484","affiliations":[{"raw_affiliation_string":"the University of Tennessee, Knoxville, United States of America","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"The University of Tennessee [Knoxville] (Knoxville, Tennessee 37996 - United States)","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010055736","display_name":"George Bosilca","orcid":"https://orcid.org/0000-0003-2411-8495"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Bosilca","raw_affiliation_strings":["the University of Tennessee, Knoxville, United States of America","The University of Tennessee [Knoxville] (Knoxville, Tennessee 37996 - United States)"],"raw_orcid":"https://orcid.org/0000-0003-2411-8495","affiliations":[{"raw_affiliation_string":"the University of Tennessee, Knoxville, United States of America","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"The University of Tennessee [Knoxville] (Knoxville, Tennessee 37996 - United States)","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054873210","display_name":"Aur\u00e9lien Bouteiller","orcid":"https://orcid.org/0000-0001-5108-509X"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aurelien Bouteiller","raw_affiliation_strings":["the University of Tennessee, Knoxville, United States of America","The University of Tennessee [Knoxville] (Knoxville, Tennessee 37996 - United States)"],"raw_orcid":"https://orcid.org/0000-0001-5108-509X","affiliations":[{"raw_affiliation_string":"the University of Tennessee, Knoxville, United States of America","institution_ids":["https://openalex.org/I75027704"]},{"raw_affiliation_string":"The University of Tennessee [Knoxville] (Knoxville, Tennessee 37996 - United States)","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085745891","display_name":"Bogdan Nicolae","orcid":"https://orcid.org/0000-0002-0661-7509"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bogdan Nicolae","raw_affiliation_strings":["Argonne National Laboratory (ANL), United States of America","ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)"],"raw_orcid":"https://orcid.org/0000-0002-0661-7509","affiliations":[{"raw_affiliation_string":"Argonne National Laboratory (ANL), United States of America","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"ANL - Argonne National Laboratory [Lemont] (9700 S Cass Ave B109, Lemont, IL, 60439 - United States)","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0871,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75130404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"44","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9887999892234802,"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":0.9887999892234802,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7682733535766602},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6404417157173157},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6282530426979065},{"id":"https://openalex.org/keywords/downtime","display_name":"Downtime","score":0.6226946115493774},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5408599376678467},{"id":"https://openalex.org/keywords/aka","display_name":"AKA","score":0.5313145518302917},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44394224882125854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40272608399391174},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15802672505378723}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682733535766602},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6404417157173157},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6282530426979065},{"id":"https://openalex.org/C180591934","wikidata":"https://www.wikidata.org/wiki/Q1253369","display_name":"Downtime","level":2,"score":0.6226946115493774},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5408599376678467},{"id":"https://openalex.org/C121158502","wikidata":"https://www.wikidata.org/wiki/Q4652161","display_name":"AKA","level":2,"score":0.5313145518302917},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44394224882125854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40272608399391174},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15802672505378723},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.1145/3624062.3626080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3626080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3626080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04343677v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04343677","pdf_url":"https://hal.science/hal-04343677/file/ULFM_hvd.pdf","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"AI4S'23: 4th Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (with SC\u201923), Nov 2023, Denver, United States. pp.44-50, ⟨10.1145/3624062.3626080⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3624062.3626080","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3624062.3626080","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3624062.3626080","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G102163711","display_name":null,"funder_award_id":"DE\u2010 AC02\u201006CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1193633358","display_name":null,"funder_award_id":"17\u2010SC\u201020\u2010SC","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1796307089","display_name":null,"funder_award_id":"17- SC-20-SC","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G3886122786","display_name":null,"funder_award_id":"17-SC20-SC","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G513797252","display_name":null,"funder_award_id":"DE-AC02\u201306CH11357","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5692331544","display_name":null,"funder_award_id":"17\u2010SC\u201020\u2010SC","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G6848031779","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6918803902","display_name":null,"funder_award_id":"06CH11357","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G7333051291","display_name":"Collaborative Research: SI2-SSI: EVOLVE: Enhancing the Open MPI Software for Next Generation Architectures and Applications","funder_award_id":"1664142","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8757742288","display_name":null,"funder_award_id":"17-SC-20-SC","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G878601127","display_name":null,"funder_award_id":"DE-AC02-06CH11357","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G993149817","display_name":null,"funder_award_id":"DE-AC02-06CH11357 ","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388581089.pdf","grobid_xml":"https://content.openalex.org/works/W4388581089.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2153958596","https://openalex.org/W2170454619","https://openalex.org/W2413047597","https://openalex.org/W2734941459","https://openalex.org/W2745999522","https://openalex.org/W2895971849","https://openalex.org/W2899071864","https://openalex.org/W2953520583","https://openalex.org/W2982612373","https://openalex.org/W3002241702","https://openalex.org/W3021124033","https://openalex.org/W3037519745","https://openalex.org/W3080198431","https://openalex.org/W3095915013","https://openalex.org/W3097875570","https://openalex.org/W3119421048","https://openalex.org/W3120931476","https://openalex.org/W3129184990","https://openalex.org/W3130587916","https://openalex.org/W3130934537","https://openalex.org/W3134991928","https://openalex.org/W3135074210","https://openalex.org/W3202350487","https://openalex.org/W4296215355","https://openalex.org/W4321485372","https://openalex.org/W6779740189","https://openalex.org/W6801890089","https://openalex.org/W6948096699"],"related_works":["https://openalex.org/W2046276983","https://openalex.org/W2954002293","https://openalex.org/W2892741875","https://openalex.org/W2164372000","https://openalex.org/W2078264086","https://openalex.org/W2109143577","https://openalex.org/W1985537075","https://openalex.org/W2161582432","https://openalex.org/W1972812226","https://openalex.org/W187383352"],"abstract_inverted_index":{"A":[0],"robust":[1],"solution":[2],"that":[3],"incorporates":[4],"fault":[5,86],"tolerance":[6],"and":[7,31,35,60,78,90,108],"elastic":[8,53,101],"scaling":[9,38],"capabilities":[10],"for":[11,85],"distributed":[12,97],"deep":[13],"learning.":[14],"Taking":[15],"advantage":[16],"of":[17,71,96],"MPI":[18,72],"resilient":[19],"capabilities,":[20],"aka.":[21],"User-Level":[22],"Failure":[23],"Mitigation":[24],"(ULFM),":[25],"this":[26],"novel":[27],"approach":[28],"promotes":[29],"efficient":[30],"lightweight":[32],"failure":[33],"management":[34],"encourages":[36],"smooth":[37],"in":[39,99,103],"volatile":[40],"computational":[41],"settings.":[42],"The":[43],"proposed":[44],"ULFM":[45,80],"MPI-centered":[46],"mechanism":[47],"outperforms":[48],"the":[49,69,93],"only":[50],"officially":[51],"supported":[52],"learning":[54,110],"framework,":[55],"Elastic":[56],"Horovod":[57],"(using":[58],"Gloo":[59],"NCCL),":[61],"by":[62],"a":[63],"significant":[64],"factor.":[65],"These":[66],"results":[67],"reinforce":[68],"capability":[70],"extension":[73],"to":[74],"deal":[75],"with":[76],"resiliency,":[77],"promote":[79],"as":[81],"an":[82],"effective":[83],"technique":[84],"management,":[87],"minimizing":[88],"downtime,":[89],"thereby":[91],"enhancing":[92],"overall":[94],"performance":[95],"applications,":[98],"particular":[100],"training":[102],"high-performance":[104],"computing":[105],"(HPC)":[106],"environments":[107],"machine":[109],"applications.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}