{"id":"https://openalex.org/W4414539025","doi":"https://doi.org/10.1109/icc52391.2025.11160856","title":"Ltfc: Loss-Tolerant Flow Control with RDMA Network for Machine Learning Clusters","display_name":"Ltfc: Loss-Tolerant Flow Control with RDMA Network for Machine Learning Clusters","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414539025","doi":"https://doi.org/10.1109/icc52391.2025.11160856"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11160856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11160856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-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/A5100354965","display_name":"Yibo Wang","orcid":"https://orcid.org/0000-0001-9984-581X"},"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":"Yibo Wang","raw_affiliation_strings":["School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371313","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0003-2696-2171"},"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":"Wei Wang","raw_affiliation_strings":["School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001549734","display_name":"Qiaojun Hu","orcid":null},"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":"Qiaojun Hu","raw_affiliation_strings":["School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776875","display_name":"Yiyang Li","orcid":"https://orcid.org/0000-0002-5809-6901"},"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":"Yiyang Li","raw_affiliation_strings":["School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700731","display_name":"Yajie Li","orcid":"https://orcid.org/0000-0002-8751-7947"},"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":"Yajie Li","raw_affiliation_strings":["School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030811766","display_name":"Yongli Zhao","orcid":"https://orcid.org/0000-0003-3716-8248"},"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":"Yongli Zhao","raw_affiliation_strings":["School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357573","display_name":"Xiaoyu Wang","orcid":"https://orcid.org/0000-0001-9411-214X"},"institutions":[{"id":"https://openalex.org/I4210130112","display_name":"China Academy of Information and Communications Technology","ror":"https://ror.org/038dte259","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210130112","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Wang","raw_affiliation_strings":["CTTL China Academy of Information and Communications Technology,Beijing,China,100191"],"affiliations":[{"raw_affiliation_string":"CTTL China Academy of Information and Communications Technology,Beijing,China,100191","institution_ids":["https://openalex.org/I4210130112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007296623","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-8073-2118"},"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":"Jie Zhang","raw_affiliation_strings":["School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"School of Electronic Engineering, Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100354965"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":2.8331,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92553612,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5343","last_page":"5348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9305999875068665,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9305999875068665,"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/retransmission","display_name":"Retransmission","score":0.6528000235557556},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.6093000173568726},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5386999845504761},{"id":"https://openalex.org/keywords/flow-control","display_name":"Flow control (data)","score":0.5232999920845032},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5001000165939331},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.4830999970436096},{"id":"https://openalex.org/keywords/packet-loss","display_name":"Packet loss","score":0.4674000144004822},{"id":"https://openalex.org/keywords/network-congestion","display_name":"Network congestion","score":0.4652999937534332},{"id":"https://openalex.org/keywords/lossless-compression","display_name":"Lossless compression","score":0.3813000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979999780654907},{"id":"https://openalex.org/C180611318","wikidata":"https://www.wikidata.org/wiki/Q7316902","display_name":"Retransmission","level":3,"score":0.6528000235557556},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.6093000173568726},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5386999845504761},{"id":"https://openalex.org/C186766456","wikidata":"https://www.wikidata.org/wiki/Q612457","display_name":"Flow control (data)","level":2,"score":0.5232999920845032},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5001000165939331},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C54108766","wikidata":"https://www.wikidata.org/wiki/Q391064","display_name":"Packet loss","level":3,"score":0.4674000144004822},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.4652999937534332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3901999890804291},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C134066672","wikidata":"https://www.wikidata.org/wiki/Q1424639","display_name":"Payload (computing)","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3785000145435333},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3720000088214874},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C180591934","wikidata":"https://www.wikidata.org/wiki/Q1253369","display_name":"Downtime","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C203274722","wikidata":"https://www.wikidata.org/wiki/Q7001161","display_name":"Network performance","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C527821871","wikidata":"https://www.wikidata.org/wiki/Q228502","display_name":"Access control","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C113508815","wikidata":"https://www.wikidata.org/wiki/Q193446","display_name":"Packet switching","level":3,"score":0.263700008392334},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11160856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11160856","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","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":16,"referenced_works":["https://openalex.org/W2083842231","https://openalex.org/W2194775991","https://openalex.org/W2498764059","https://openalex.org/W2558580397","https://openalex.org/W2809353470","https://openalex.org/W2891983498","https://openalex.org/W2926543120","https://openalex.org/W2964412985","https://openalex.org/W2968108410","https://openalex.org/W2968755040","https://openalex.org/W3004095116","https://openalex.org/W3093895572","https://openalex.org/W4235732943","https://openalex.org/W4240522432","https://openalex.org/W4246193833","https://openalex.org/W4389161427"],"related_works":[],"abstract_inverted_index":{"Current":[0],"AI":[1],"training":[2],"clusters":[3],"widely":[4],"use":[5],"RoCEv2":[6,18],"to":[7,25,49,88,94,104,130,168,176,180],"improve":[8],"the":[9,13,51,100,105,111,114,136,147,160],"communication":[10],"efficiency":[11],"of":[12,71,140,149],"interconnect":[14],"networks":[15],"across":[16],"machines.":[17],"relies":[19],"on":[20,86,142],"Priority":[21],"Flow":[22],"Control":[23],"(PFC)":[24],"ensure":[26,89],"a":[27,77,90,127],"lossless":[28,91],"network.":[29],"However,":[30,54],"PFC":[31,87,115],"brings":[32],"certain":[33],"side":[34,52],"effects,":[35],"such":[36],"as":[37],"head-of-line":[38],"blocking,":[39],"congestion":[40],"spreading,":[41],"and":[42,145,171],"deadlock.":[43],"Numerous":[44],"studies":[45],"have":[46],"been":[47],"proposed":[48],"eliminate":[50,131],"effects.":[53],"unlike":[55],"traditional":[56,106],"high-performance":[57],"computing":[58],"applications,":[59],"distributed":[60],"machine":[61],"learning":[62],"(DML)":[63],"is":[64],"not":[65,84],"100":[66],"%":[67,170,178],"loss-intolerant.":[68],"In":[69],"light":[70],"this":[72,74],"observation,":[73],"paper":[75],"proposes":[76],"loss-tolerant":[78],"flow":[79,162],"control":[80,95],"(LTFC).":[81],"LTFC":[82,109,150,158],"does":[83],"rely":[85],"environment,":[92],"but":[93],"packet":[96],"loss":[97],"ratio":[98],"within":[99],"tolerance":[101,138],"threshold.":[102],"Compared":[103],"trigger":[107],"condition,":[108],"reduces":[110,159],"likelihood":[112],"that":[113,157],"will":[116],"be":[117],"triggered.":[118],"Additionally,":[119],"we":[120],"replace":[121],"RoCEv2's":[122],"default":[123],"Go-back-N":[124],"mechanism":[125,129],"with":[126],"non-retransmission":[128],"retransmission":[132],"latency.":[133],"We":[134],"demonstrate":[135],"bounded-loss":[137],"feature":[139],"DML":[141],"our":[143],"testbed":[144],"evaluate":[146],"performance":[148],"in":[151],"large-scale":[152],"simulations.":[153],"Simulation":[154],"results":[155],"show":[156],"average":[161],"completion":[163],"time":[164],"(FCT)":[165],"by":[166,174],"up":[167,175],"26.9":[169],"tail":[172],"FCT":[173],"16.9":[177],"compared":[179],"existing":[181],"solutions.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}