{"id":"https://openalex.org/W4404242365","doi":"https://doi.org/10.1007/s11704-023-3401-5","title":"BAFT: bubble-aware fault-tolerant framework for distributed DNN training with hybrid parallelism","display_name":"BAFT: bubble-aware fault-tolerant framework for distributed DNN training with hybrid parallelism","publication_year":2024,"publication_date":"2024-11-11","ids":{"openalex":"https://openalex.org/W4404242365","doi":"https://doi.org/10.1007/s11704-023-3401-5"},"language":"en","primary_location":{"id":"doi:10.1007/s11704-023-3401-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11704-023-3401-5","pdf_url":null,"source":{"id":"https://openalex.org/S4210231404","display_name":"Frontiers of Computer Science","issn_l":"2095-2228","issn":["2095-2228","2095-2236"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311889","host_organization_name":"Higher Education Press","host_organization_lineage":["https://openalex.org/P4310311889"],"host_organization_lineage_names":["Higher Education Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Computer Science","raw_type":"journal-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/A5042923080","display_name":"Runzhe Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runzhe Chen","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","Shanghai Qi Zhi Institution, Shanghai, 200232, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institution, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080711460","display_name":"Guandong Lu","orcid":"https://orcid.org/0009-0000-6759-9108"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guandong Lu","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","Shanghai Qi Zhi Institution, Shanghai, 200232, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institution, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084399347","display_name":"Yakai Wang","orcid":"https://orcid.org/0009-0009-0835-6304"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yakai Wang","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","Shanghai Qi Zhi Institution, Shanghai, 200232, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institution, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101812274","display_name":"Zhang Rui","orcid":"https://orcid.org/0009-0008-3887-9344"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["Huawei Technologies Co., Ltd, Shenzhen, 518129, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd, Shenzhen, 518129, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088928758","display_name":"Zheng Hu","orcid":"https://orcid.org/0000-0002-3526-0297"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Hu","raw_affiliation_strings":["Huawei Technologies Co., Ltd, Shenzhen, 518129, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd, Shenzhen, 518129, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021024149","display_name":"Yanming Miao","orcid":"https://orcid.org/0009-0004-3244-2660"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanming Miao","raw_affiliation_strings":["Huawei Technologies Co., Ltd, Shenzhen, 518129, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd, Shenzhen, 518129, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007762289","display_name":"Zhifang Cai","orcid":"https://orcid.org/0009-0000-4756-8806"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhifang Cai","raw_affiliation_strings":["Huawei Technologies Co., Ltd, Shenzhen, 518129, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd, Shenzhen, 518129, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003939279","display_name":"Jingwen Leng","orcid":"https://orcid.org/0000-0002-5660-5493"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Leng","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","Shanghai Qi Zhi Institution, Shanghai, 200232, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institution, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Minyi Guo","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","Shanghai Qi Zhi Institution, Shanghai, 200232, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institution, Shanghai, 200232, China","institution_ids":["https://openalex.org/I4210122302"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5039318240"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210122302"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":1.8093,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.866943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"19","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9986000061035156,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9986000061035156,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9940999746322632,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.922573447227478},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.7250993847846985},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.671419620513916},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5554323792457581},{"id":"https://openalex.org/keywords/bubble","display_name":"Bubble","score":0.5036808848381042},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4279821515083313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.922573447227478},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.7250993847846985},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.671419620513916},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5554323792457581},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.5036808848381042},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4279821515083313}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11704-023-3401-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11704-023-3401-5","pdf_url":null,"source":{"id":"https://openalex.org/S4210231404","display_name":"Frontiers of Computer Science","issn_l":"2095-2228","issn":["2095-2228","2095-2236"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311889","host_organization_name":"Higher Education Press","host_organization_lineage":["https://openalex.org/P4310311889"],"host_organization_lineage_names":["Higher Education Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Computer Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1493428480","https://openalex.org/W2602856279","https://openalex.org/W2610373075","https://openalex.org/W2618530766","https://openalex.org/W2911293880","https://openalex.org/W2912083425","https://openalex.org/W2913584116","https://openalex.org/W2914062858","https://openalex.org/W2914304175","https://openalex.org/W3020414749","https://openalex.org/W3086105743","https://openalex.org/W3143835353","https://openalex.org/W4226064176"],"related_works":["https://openalex.org/W2072214669","https://openalex.org/W1595672120","https://openalex.org/W4230999561","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":null,"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}
