{"id":"https://openalex.org/W6903438425","doi":"https://doi.org/10.1145/3735358.3735378","title":"Congestion Control for AI Workloads with Message-Level Signaling","display_name":"Congestion Control for AI Workloads with Message-Level Signaling","publication_year":2025,"publication_date":"2025-07-17","ids":{"openalex":"https://openalex.org/W6903438425","doi":"https://doi.org/10.1145/3735358.3735378"},"language":"en","primary_location":{"id":"doi:10.1145/3735358.3735378","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735358.3735378","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3735358.3735378","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuxuan Li","orcid":"https://orcid.org/0009-0003-9042-7285"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuxuan Li","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0003-9042-7285","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenghang Ren","orcid":"https://orcid.org/0000-0002-8779-4768"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhenghang Ren","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8779-4768","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenxue Li","orcid":"https://orcid.org/0000-0002-8228-2552"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenxue Li","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8228-2552","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangzhou Liu","orcid":"https://orcid.org/0009-0000-2156-9683"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiangzhou Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0000-2156-9683","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kai Chen","orcid":"https://orcid.org/0000-0003-2587-6028"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-2587-6028","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":1.6049,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86644128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.8116999864578247,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.8116999864578247,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.04010000079870224,"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"}},{"id":"https://openalex.org/T10138","display_name":"Network Traffic and Congestion Control","score":0.015399999916553497,"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/network-congestion","display_name":"Network congestion","score":0.7281000018119812},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5856000185012817},{"id":"https://openalex.org/keywords/packet-loss","display_name":"Packet loss","score":0.5062000155448914},{"id":"https://openalex.org/keywords/flow-control","display_name":"Flow control (data)","score":0.49079999327659607},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.46320000290870667},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.4537000060081482},{"id":"https://openalex.org/keywords/traffic-congestion","display_name":"Traffic congestion","score":0.3684000074863434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.79339998960495},{"id":"https://openalex.org/C195563490","wikidata":"https://www.wikidata.org/wiki/Q180368","display_name":"Network congestion","level":3,"score":0.7281000018119812},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5146999955177307},{"id":"https://openalex.org/C54108766","wikidata":"https://www.wikidata.org/wiki/Q391064","display_name":"Packet loss","level":3,"score":0.5062000155448914},{"id":"https://openalex.org/C186766456","wikidata":"https://www.wikidata.org/wiki/Q612457","display_name":"Flow control (data)","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.46320000290870667},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43810001015663147},{"id":"https://openalex.org/C2779888511","wikidata":"https://www.wikidata.org/wiki/Q244156","display_name":"Traffic congestion","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C164916973","wikidata":"https://www.wikidata.org/wiki/Q1378386","display_name":"Leaky bucket","level":3,"score":0.3147999942302704},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30570000410079956},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C193519340","wikidata":"https://www.wikidata.org/wiki/Q891179","display_name":"Data loss","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3735358.3735378","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735358.3735378","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-165762","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-165762","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3735358.3735378","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3735358.3735378","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1978175770","https://openalex.org/W2038718790","https://openalex.org/W2087178199","https://openalex.org/W2103110737","https://openalex.org/W2126969025","https://openalex.org/W2157990152","https://openalex.org/W2174359540","https://openalex.org/W2498764059","https://openalex.org/W2809353470","https://openalex.org/W2892909727","https://openalex.org/W2968108410","https://openalex.org/W4235732943","https://openalex.org/W4290991080","https://openalex.org/W4400682099","https://openalex.org/W4401176521","https://openalex.org/W4401176799","https://openalex.org/W4407197371"],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"AI":[1,171],"training":[2,103],"is":[3,134,165,188],"among":[4],"the":[5,107,149,185,192,215,220],"most":[6],"demanding":[7],"workloads":[8],"in":[9,98,101,208,234],"datacenter":[10],"networks.":[11],"The":[12,131],"unique":[13],"characteristics":[14],"of":[15,219],"low":[16],"flow":[17,20,50],"entropy":[18],"exacerbate":[19],"collisions":[21],"under":[22],"traditional":[23],"Equal-Cost-Multi-Path":[24],"(ECMP)":[25],"Load":[26],"Balance":[27],"(LB).":[28],"To":[29,105],"mitigate":[30],"these":[31,155],"issues,":[32],"per-packet":[33,54,74,113,144,168],"LB":[34,55,169],"mechanisms,":[35],"such":[36],"as":[37,44,120],"packet":[38],"spraying":[39],"and":[40,71,112,179,198,217],"adaptive":[41],"routing,":[42],"emerge":[43],"a":[45,121,160,176,202],"promising":[46],"alternative":[47,124],"to":[48,59,73,93,125,135,146,195,205],"eliminate":[49],"collisions.":[51],"However,":[52],"since":[53],"inherently":[56],"rebalances":[57],"traffic":[58,207],"absorb":[60],"partial":[61],"congestion,":[62],"existing":[63],"Congestion":[64],"Control":[65],"(CC)":[66],"algorithms":[67],"overlook":[68],"this":[69,90],"behavior":[70],"overreact":[72],"congestion":[75,82,85,127,151,161,231],"signals":[76,119],"which":[77],"only":[78,183],"reflect":[79],"individual":[80],"path":[81],"rather":[83,139],"than":[84,140],"across":[86,128],"multiple":[87,129],"paths.":[88,130],"Consequently,":[89],"overreaction":[91,233],"leads":[92],"unnecessary":[94],"rate":[95],"reductions,":[96],"resulting":[97],"throughput":[99],"degradation":[100],"model":[102],"processes.":[104],"tackle":[106],"incompatibility":[108],"between":[109],"current":[110],"CC":[111],"LB,":[114],"we":[115,157],"propose":[116],"using":[117],"message-level":[118],"more":[122],"accurate":[123],"capture":[126,148],"key":[132],"idea":[133],"leverage":[136],"message":[137],"delays":[138,145],"solely":[141],"relying":[142],"on":[143,154],"better":[147],"global":[150,186],"state.":[152],"Based":[153],"signals,":[156],"build":[158],"MCC,":[159],"control":[162,206],"mechanism":[163],"that":[164,227],"compatible":[166],"with":[167],"for":[170],"workloads.":[172],"Specifically,":[173],"MCC":[174,200,228],"adopts":[175,201],"window-based":[177],"approach":[178,204],"reduces":[180],"in-flight":[181],"data":[182],"when":[184],"pipe":[187],"congested.":[189],"Furthermore,":[190],"considering":[191],"challenges":[193],"related":[194],"hardware":[196],"programmability":[197],"compatibility,":[199],"software-based":[203],"collective":[209,235],"communication":[210,236],"libraries":[211],"(CCLs),":[212],"achieving":[213],"both":[214],"efficiency":[216],"independence":[218],"NIC":[221],"hardware.":[222],"Our":[223],"simulation":[224],"results":[225],"demonstrate":[226],"effectively":[229],"alleviates":[230],"without":[232],"operations.":[237]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}
