{"id":"https://openalex.org/W7204041382","doi":"https://doi.org/10.1007/978-981-92-4805-6_18","title":"C$$^{3}$$FT: Computation-Centric Checkpointing for Distributed Large Model Training","display_name":"C$$^{3}$$FT: Computation-Centric Checkpointing for Distributed Large Model Training","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204041382","doi":"https://doi.org/10.1007/978-981-92-4805-6_18"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-4805-6_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-4805-6_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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":"https://openalex.org/A5101802996","display_name":"Yonghua Huang","orcid":"https://orcid.org/0000-0002-0366-9768"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghua Huang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-2331-0108","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147899171","display_name":"Baodong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baodong Wu","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088172355","display_name":"Shigang Li","orcid":"https://orcid.org/0000-0003-0022-7865"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shigang Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0022-7865","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006252544","display_name":"Jiahao Ding","orcid":"https://orcid.org/0000-0002-2867-4133"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Ding","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065684265","display_name":"Rongtian Fu","orcid":"https://orcid.org/0009-0008-7636-3082"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongtian Fu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147904326","display_name":"Qingping Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingping Li","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001407617","display_name":"Boxun Li","orcid":"https://orcid.org/0000-0002-6132-7547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boxun Li","raw_affiliation_strings":["Infinigence-AI, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068626165","display_name":"Zhenhua Zhu","orcid":"https://orcid.org/0000-0002-4554-1770"},"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":"Zhenhua Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147891596","display_name":"Yu Wang","orcid":null},"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":"Yu Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088172355"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"269","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.8144999742507935},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.76419997215271},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.659500002861023},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5577999949455261},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.48100000619888306},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.38760000467300415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805999755859375},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8144999742507935},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.76419997215271},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.659500002861023},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5407000184059143},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.48100000619888306},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C167391956","wikidata":"https://www.wikidata.org/wiki/Q1401211","display_name":"Fault model","level":3,"score":0.38530001044273376},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.32600000500679016},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3111000061035156},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25940001010894775},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-4805-6_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-4805-6_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2087402357","https://openalex.org/W3081168214","https://openalex.org/W3129831491","https://openalex.org/W4321446170","https://openalex.org/W4387302750","https://openalex.org/W4390097689","https://openalex.org/W4408903192","https://openalex.org/W4409248832"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2026-08-24T00:00:00"}
