{"id":"https://openalex.org/W4379033976","doi":"https://doi.org/10.1109/tmc.2023.3272567","title":"FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Approach for Heterogeneous Edge Devices","display_name":"FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Approach for Heterogeneous Edge Devices","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4379033976","doi":"https://doi.org/10.1109/tmc.2023.3272567"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2023.3272567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2023.3272567","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","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/A5100321270","display_name":"Yuhao Chen","orcid":"https://orcid.org/0000-0002-9905-5823"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhao Chen","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010220478","display_name":"Qianqian Yang","orcid":"https://orcid.org/0000-0003-4747-9410"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianqian Yang","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068195118","display_name":"Shibo He","orcid":"https://orcid.org/0000-0002-1505-6766"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shibo He","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041940889","display_name":"Zhiguo Shi","orcid":"https://orcid.org/0000-0001-9160-048X"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiguo Shi","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100726041","display_name":"Jiming Chen","orcid":"https://orcid.org/0000-0003-3155-3145"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiming Chen","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057916222","display_name":"Mohsen Guizani","orcid":"https://orcid.org/0000-0002-8972-8094"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohsen Guizani","raw_affiliation_strings":["Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE"],"affiliations":[{"raw_affiliation_string":"Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100321270"],"corresponding_institution_ids":["https://openalex.org/I4391767838"],"apc_list":null,"apc_paid":null,"fwci":2.7481,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92123878,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"23","issue":"4","first_page":"3200","last_page":"3212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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/T13553","display_name":"Age of Information Optimization","score":0.998199999332428,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.8763915300369263},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6933083534240723},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6604921817779541},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.6254943609237671},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5971300601959229},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5484493374824524},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5242629051208496},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5207512378692627},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4935685396194458},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4858569800853729},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.46532151103019714},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4613369405269623},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4335760176181793},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41419151425361633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38579580187797546},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11171340942382812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8763915300369263},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6933083534240723},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6604921817779541},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.6254943609237671},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5971300601959229},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5484493374824524},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5242629051208496},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5207512378692627},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4935685396194458},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4858569800853729},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.46532151103019714},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4613369405269623},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4335760176181793},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41419151425361633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38579580187797546},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11171340942382812},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2023.3272567","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2023.3272567","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2464562129","display_name":null,"funder_award_id":"2021C03037","funder_id":"https://openalex.org/F8142712028","funder_display_name":"Key Research and Development Program of Zhejiang Province"},{"id":"https://openalex.org/G4710423954","display_name":null,"funder_award_id":"62201505","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6454029087","display_name":null,"funder_award_id":"62293481","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8010306742","display_name":null,"funder_award_id":"U21A20456","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8022898299","display_name":null,"funder_award_id":"U1909207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8398014063","display_name":null,"funder_award_id":"2021FZZX001-20","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F8142712028","display_name":"Key Research and Development Program of Zhejiang Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2530417694","https://openalex.org/W2535838896","https://openalex.org/W2560647685","https://openalex.org/W2587770880","https://openalex.org/W2610332124","https://openalex.org/W2769100446","https://openalex.org/W2777460464","https://openalex.org/W2806506455","https://openalex.org/W2963163009","https://openalex.org/W2964223234","https://openalex.org/W2967314080","https://openalex.org/W2981114133","https://openalex.org/W2983307807","https://openalex.org/W2990155362","https://openalex.org/W3008133786","https://openalex.org/W3015447160","https://openalex.org/W3018464563","https://openalex.org/W3024862772","https://openalex.org/W3049640275","https://openalex.org/W3088405768","https://openalex.org/W3102767875","https://openalex.org/W3109233295","https://openalex.org/W3162873931","https://openalex.org/W3176786489","https://openalex.org/W3185341429","https://openalex.org/W4236099117","https://openalex.org/W4246399668","https://openalex.org/W4293775467","https://openalex.org/W4297687186","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W6605479355","https://openalex.org/W6728757088","https://openalex.org/W6737664043","https://openalex.org/W6752367771"],"related_works":["https://openalex.org/W4322761281","https://openalex.org/W4238233472","https://openalex.org/W4313526662","https://openalex.org/W3111395152","https://openalex.org/W4312996489","https://openalex.org/W3106131444","https://openalex.org/W3216099748","https://openalex.org/W4205963435","https://openalex.org/W4313463379","https://openalex.org/W3214037210"],"abstract_inverted_index":{"With":[0],"the":[1,15,29,58,64,70,73,95,100,103,112,131,135,139,145,170,174,178,186,194,201,205],"increasing":[2],"proliferation":[3],"of":[4,17,45,57,107,147,177,207],"Internet-of-Things":[5],"(IoT)":[6],"devices,":[7],"there":[8],"is":[9,163,181,190,197],"a":[10,81,124],"growing":[11],"trend":[12],"towards":[13],"distributing":[14,63],"power":[16,106],"deep":[18,33,46],"learning":[19],"(DL)":[20],"among":[21],"edge":[22,38],"devices":[23,39,93,149],"rather":[24],"than":[25,169,185],"centralizing":[26],"it":[27],"at":[28,37,72],"cloud.":[30,74],"To":[31,98],"deploy":[32],"and":[34,138],"complex":[35],"models":[36,50,89],"with":[40,94,102,204],"limited":[41,154],"resources,":[42],"model":[43,66,71],"partitioning":[44],"neural":[47],"network":[48],"(DNN)":[49],"has":[51],"been":[52],"widely":[53],"studied.":[54],"However,":[55],"most":[56],"existing":[59],"literature":[60],"only":[61],"considers":[62],"inference":[65],"while":[67,152],"still":[68],"training":[69,84,101,151,168,202],"In":[75],"this":[76],"paper,":[77],"we":[78,110],"propose":[79,123],"FTPipeHD,":[80],"novel":[82,125],"DNN":[83,88],"approach":[85,128],"that":[86,129,161,193],"trains":[87],"across":[90],"distributed":[91],"heterogeneous":[92],"fault-tolerance":[96],"mechanism.":[97],"accelerate":[99,200],"time-varying":[104],"computing":[105,119,175],"each":[108],"device,":[109],"optimize":[111],"partition":[113],"points":[114],"dynamically":[115],"according":[116],"to":[117,133,199],"real-time":[118],"capacities.":[120],"We":[121],"also":[122,191],"weight":[126],"redistribution":[127],"replicates":[130],"weights":[132],"both":[134],"neighboring":[136],"nodes":[137],"central":[140],"node":[141],"periodically,":[142],"which":[143],"combats":[144],"failure":[146],"multiple":[148],"during":[150],"incurring":[153],"communication":[155],"costs.":[156],"Our":[157],"numerical":[158],"results":[159],"demonstrate":[160],"FTPipeHD":[162],"6.8":[164],"times":[165,183],"faster":[166],"in":[167],"state-of-the-art":[171],"method":[172,196],"when":[173],"capacity":[176],"best":[179],"device":[180,208],"10":[182],"greater":[184],"worst":[187],"one.":[188],"It":[189],"shown":[192],"proposed":[195],"able":[198],"even":[203],"existence":[206],"failures.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}