{"id":"https://openalex.org/W4385367428","doi":"https://doi.org/10.1109/iwqos57198.2023.10188699","title":"Boosting Distributed Machine Learning Training Through Loss-tolerant Transmission Protocol","display_name":"Boosting Distributed Machine Learning Training Through Loss-tolerant Transmission Protocol","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4385367428","doi":"https://doi.org/10.1109/iwqos57198.2023.10188699"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos57198.2023.10188699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos57198.2023.10188699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},"type":"preprint","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/A5101458538","display_name":"Zixuan Chen","orcid":"https://orcid.org/0000-0002-0126-0387"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zixuan Chen","raw_affiliation_strings":["School of Computer Science, Fudan University,Shanghai,China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499716","display_name":"Lei Shi","orcid":"https://orcid.org/0009-0004-0649-5443"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Shi","raw_affiliation_strings":["School of Computer Science, Fudan University,Shanghai,China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102778994","display_name":"Xuandong Liu","orcid":"https://orcid.org/0009-0002-6521-6200"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuandong Liu","raw_affiliation_strings":["School of Computer Science, Fudan University,Shanghai,China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048767437","display_name":"Xin Ai","orcid":"https://orcid.org/0000-0001-6079-5237"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Ai","raw_affiliation_strings":["School of Computer Science, Fudan University,Shanghai,China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358497","display_name":"Sen Liu","orcid":"https://orcid.org/0000-0003-2230-7671"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Liu","raw_affiliation_strings":["School of Computer Science, Fudan University,Shanghai,China","School of Computer Science, Fudan University, Shanghai, China","Institute of Fintech, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Institute of Fintech, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014490044","display_name":"Yang Xu","orcid":"https://orcid.org/0000-0002-0958-8547"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xu","raw_affiliation_strings":["School of Computer Science, Fudan University,Shanghai,China","Peng Cheng Laboratory, Shenzhen, China","School of Computer Science, Fudan University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101458538"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.3156,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80271318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9986000061035156,"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/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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7685739398002625},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6000469326972961},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.5319101214408875},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4630489647388458},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.45144930481910706},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34308958053588867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22795841097831726},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.12622222304344177},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1129285991191864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685739398002625},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6000469326972961},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5319101214408875},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4630489647388458},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.45144930481910706},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34308958053588867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22795841097831726},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.12622222304344177},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1129285991191864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos57198.2023.10188699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos57198.2023.10188699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1963915651","https://openalex.org/W1975934607","https://openalex.org/W1980287119","https://openalex.org/W2022844530","https://openalex.org/W2103110737","https://openalex.org/W2118889957","https://openalex.org/W2119942658","https://openalex.org/W2138243089","https://openalex.org/W2177838837","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2259472270","https://openalex.org/W2407022425","https://openalex.org/W2416799949","https://openalex.org/W2530088943","https://openalex.org/W2545990795","https://openalex.org/W2605350416","https://openalex.org/W2606891064","https://openalex.org/W2622263826","https://openalex.org/W2751904527","https://openalex.org/W2769644379","https://openalex.org/W2794896506","https://openalex.org/W2899592413","https://openalex.org/W2900071409","https://openalex.org/W2922527104","https://openalex.org/W2963728985","https://openalex.org/W2963819344","https://openalex.org/W2964412985","https://openalex.org/W2967314080","https://openalex.org/W2974170798","https://openalex.org/W2994839823","https://openalex.org/W2997709794","https://openalex.org/W3015977727","https://openalex.org/W3101036738","https://openalex.org/W3105875719","https://openalex.org/W3118608800","https://openalex.org/W3138562521","https://openalex.org/W3138920078","https://openalex.org/W3204921648","https://openalex.org/W4302802882","https://openalex.org/W6680402377","https://openalex.org/W6685682220","https://openalex.org/W6692563993","https://openalex.org/W6728757088","https://openalex.org/W6736413256","https://openalex.org/W6739622702","https://openalex.org/W6746200960","https://openalex.org/W6746839373","https://openalex.org/W6754416507","https://openalex.org/W6760703128","https://openalex.org/W6763393679","https://openalex.org/W6794216301"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W4285042611","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2338718585"],"abstract_inverted_index":{"Distributed":[0],"Machine":[1],"Learning":[2],"(DML)":[3],"systems":[4],"are":[5],"utilized":[6],"to":[7,65,71,91,105,142,145,153],"enhance":[8],"the":[9,52,93],"speed":[10],"of":[11,61,122],"model":[12],"training":[13,44,107,137],"in":[14],"data":[15,103],"centers":[16],"(DCs)":[17],"and":[18,69,83,100,114,126],"edge":[19],"nodes.":[20],"The":[21],"Parameter":[22],"Server":[23],"(PS)":[24],"communication":[25],"architecture":[26],"is":[27,110],"commonly":[28],"employed,":[29],"but":[30],"it":[31],"faces":[32],"severe":[33],"long-tail":[34],"latency":[35],"caused":[36],"by":[37,112,140],"many-to-one":[38],"\u201cincast\u201d":[39],"traffic":[40],"patterns,":[41],"negatively":[42],"impacting":[43],"throughput.":[45],"To":[46],"address":[47],"this":[48],"challenge,":[49],"we":[50],"design":[51],"Loss-tolerant":[53],"Transmission":[54],"Protocol":[55],"(LTP),":[56],"which":[57],"permits":[58],"partial":[59],"loss":[60],"gradients":[62],"during":[63],"synchronization":[64,73],"avoid":[66],"unneeded":[67],"retransmission":[68],"contributes":[70],"faster":[72],"per":[74],"iteration.":[75],"LTP":[76,87,109,132],"implements":[77],"loss-tolerant":[78,94],"transmission":[79,82],"through":[80],"out-of-order":[81,84],"Acknowledges":[85],"(ACKs).":[86],"employs":[88],"Early":[89],"Close":[90],"adjust":[92],"threshold":[95],"based":[96],"on":[97,119],"network":[98],"conditions":[99],"bubble-filling":[101],"for":[102],"correction":[104],"maintain":[106],"accuracy.":[108,155],"implemented":[111],"C++":[113],"integrated":[115],"into":[116],"PyTorch.":[117],"Evaluations":[118],"a":[120],"testbed":[121],"8":[123],"worker":[124],"nodes":[125],"one":[127],"PS":[128],"node":[129],"demonstrate":[130],"that":[131],"can":[133],"significantly":[134],"improve":[135],"DML":[136],"task":[138],"throughput":[139],"up":[141],"30x":[143],"compared":[144],"traditional":[146],"TCP":[147],"congestion":[148],"controls,":[149],"with":[150],"no":[151],"sacrifice":[152],"final":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-07-29T00:00:00"}