{"id":"https://openalex.org/W4402775336","doi":"https://doi.org/10.1109/tnsm.2024.3461875","title":"A Fine-Grained Packet Loss Tolerance Transmission Algorithm for Communication Optimization in Distributed Deep Learning","display_name":"A Fine-Grained Packet Loss Tolerance Transmission Algorithm for Communication Optimization in Distributed Deep Learning","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402775336","doi":"https://doi.org/10.1109/tnsm.2024.3461875"},"language":"en","primary_location":{"id":"doi:10.1109/tnsm.2024.3461875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2024.3461875","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Network and Service Management","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/A5004715828","display_name":"Yifei Lu","orcid":"https://orcid.org/0000-0002-1352-5418"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifei Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1352-5418","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102857137","display_name":"Jingqi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqi Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109787922","display_name":"Shuren Li","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuren Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005438005","display_name":"Chanying Huang","orcid":"https://orcid.org/0000-0002-1314-4949"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chanying Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.6054,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69385423,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"21","issue":"6","first_page":"6112","last_page":"6125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9635000228881836,"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9635000228881836,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.9456999897956848,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8500611782073975},{"id":"https://openalex.org/keywords/packet-loss","display_name":"Packet loss","score":0.5092767477035522},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.5029248595237732},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.47582533955574036},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.47471725940704346},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39809858798980713},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39372530579566956},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14410072565078735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500611782073975},{"id":"https://openalex.org/C54108766","wikidata":"https://www.wikidata.org/wiki/Q391064","display_name":"Packet loss","level":3,"score":0.5092767477035522},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.5029248595237732},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.47582533955574036},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.47471725940704346},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39809858798980713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39372530579566956},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14410072565078735}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnsm.2024.3461875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2024.3461875","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Network and Service Management","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5552475107","display_name":null,"funder_award_id":"2020YFB1805503","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8931858883","display_name":null,"funder_award_id":"61702267","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W1980287119","https://openalex.org/W2016053056","https://openalex.org/W2057332538","https://openalex.org/W2083842231","https://openalex.org/W2160815625","https://openalex.org/W2508010313","https://openalex.org/W2594041104","https://openalex.org/W2896457183","https://openalex.org/W2919115771","https://openalex.org/W2920397365","https://openalex.org/W2963433607","https://openalex.org/W2964412985","https://openalex.org/W2969388332","https://openalex.org/W2972087877","https://openalex.org/W2975712713","https://openalex.org/W2991040477","https://openalex.org/W3071522630","https://openalex.org/W4232411329","https://openalex.org/W4242648275","https://openalex.org/W4290996662","https://openalex.org/W4327909439","https://openalex.org/W4366393886","https://openalex.org/W4385367428","https://openalex.org/W4394922822","https://openalex.org/W4395085346","https://openalex.org/W4400236913","https://openalex.org/W6631190155","https://openalex.org/W6679393576","https://openalex.org/W6682132143","https://openalex.org/W6736413256","https://openalex.org/W6739693220","https://openalex.org/W6745723224","https://openalex.org/W6746200960","https://openalex.org/W6746839373","https://openalex.org/W6751815326","https://openalex.org/W6754818105","https://openalex.org/W6756009870","https://openalex.org/W6758283263","https://openalex.org/W6759814162","https://openalex.org/W6762211661","https://openalex.org/W7052937856"],"related_works":["https://openalex.org/W4379116402","https://openalex.org/W2111375262","https://openalex.org/W1991205173","https://openalex.org/W2376837861","https://openalex.org/W2109048960","https://openalex.org/W2271593509","https://openalex.org/W2741481635","https://openalex.org/W2595752737","https://openalex.org/W3199712142","https://openalex.org/W2134402536"],"abstract_inverted_index":{"Communication":[0],"overhead":[1,102],"is":[2],"a":[3,93,115],"significant":[4],"challenge":[5],"in":[6,56],"distributed":[7],"deep":[8],"learning":[9],"(DDL)":[10],"training,":[11],"often":[12,32],"hindering":[13],"efficiency.":[14],"While":[15],"existing":[16],"solutions":[17],"like":[18],"gradient":[19,120],"compression,":[20],"compute/communication":[21],"overlap,":[22],"and":[23,34,127,141,155],"layer-wise":[24],"flow":[25,47],"scheduling":[26],"have":[27],"been":[28],"proposed,":[29],"they":[30],"are":[31],"coarse-grained":[33],"insufficient,":[35],"especially":[36],"under":[37],"network":[38],"congestion.":[39],"These":[40],"congestion-unaware":[41],"methods":[42,69],"can":[43,70],"lead":[44],"to":[45],"long":[46],"completion":[48],"times,":[49],"known":[50],"as":[51],"the":[52,72,81,105,110,123],"tail":[53,73,124,153],"latency,":[54],"resulting":[55],"extended":[57],"training":[58,78,129,157],"time.":[59,158],"In":[60],"this":[61],"paper,":[62],"we":[63],"argue":[64],"that":[65,145],"packet":[66,95,132],"loss":[67,96,107,133],"tolerance":[68,82,97,108],"mitigate":[71],"latency":[74,125,154],"issue":[75,126],"without":[76],"sacrificing":[77],"accuracy,":[79],"with":[80],"bound":[83],"varying":[84],"across":[85],"different":[86],"DDL":[87,156],"model":[88],"layers.":[89],"We":[90],"introduce":[91],"PLOT,":[92],"fine-grained":[94],"algorithm,":[98],"which":[99],"optimizes":[100],"communication":[101],"by":[103],"leveraging":[104],"layer-specific":[106],"of":[109],"DNN":[111],"model.":[112],"PLOT":[113,146],"employs":[114],"UDP-based":[116],"transmission":[117],"mechanism":[118],"for":[119],"transfer,":[121],"addressing":[122],"maintaining":[128],"accuracy":[130],"through":[131],"tolerance.":[134],"Our":[135],"evaluations":[136],"on":[137],"both":[138],"small-scale":[139],"testbeds":[140],"large-scale":[142],"simulations":[143],"show":[144],"outperforms":[147],"other":[148],"congestion":[149],"algorithms,":[150],"effectively":[151],"reducing":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}