{"id":"https://openalex.org/W4385357021","doi":"https://doi.org/10.1109/iwqos57198.2023.10188783","title":"GOAT: Gradient Scheduling with Collaborative In-Network Aggregation for Distributed Training","display_name":"GOAT: Gradient Scheduling with Collaborative In-Network Aggregation for Distributed Training","publication_year":2023,"publication_date":"2023-06-19","ids":{"openalex":"https://openalex.org/W4385357021","doi":"https://doi.org/10.1109/iwqos57198.2023.10188783"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos57198.2023.10188783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos57198.2023.10188783","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":"conference-paper","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/A5010510283","display_name":"J. H. Fang","orcid":"https://orcid.org/0000-0003-4222-1971"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Fang","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China","Suzhou Institute for Advanced Research, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074187380","display_name":"Gongming Zhao","orcid":"https://orcid.org/0000-0003-1311-8908"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongming Zhao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China","Suzhou Institute for Advanced Research, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063184427","display_name":"Hongli Xu","orcid":"https://orcid.org/0000-0003-3831-4577"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongli Xu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China","Suzhou Institute for Advanced Research, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007816619","display_name":"Zhuolong Yu","orcid":"https://orcid.org/0000-0002-8846-5229"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuolong Yu","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079797656","display_name":"Bingchen Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingchen Shen","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China","Suzhou Institute for Advanced Research, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040158607","display_name":"Liguang Xie","orcid":"https://orcid.org/0000-0002-3764-9888"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liguang Xie","raw_affiliation_strings":["Virginia Tech,USA","Virginia Tech, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech,USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9986000061035156,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9986000061035156,"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":0.9871000051498413,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9811000227928162,"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":0.679715633392334},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5551856160163879},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49247273802757263},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4623253643512726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33904439210891724},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.11588490009307861},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09622687101364136},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06094279885292053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679715633392334},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5551856160163879},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49247273802757263},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4623253643512726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33904439210891724},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.11588490009307861},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09622687101364136},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06094279885292053},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos57198.2023.10188783","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos57198.2023.10188783","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":[{"id":"https://openalex.org/G3189050608","display_name":null,"funder_award_id":"62102392,62132019","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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1563795667","https://openalex.org/W2014369282","https://openalex.org/W2060393849","https://openalex.org/W2117539524","https://openalex.org/W2130531694","https://openalex.org/W2194775991","https://openalex.org/W2463357960","https://openalex.org/W2493244360","https://openalex.org/W2617766261","https://openalex.org/W2751108192","https://openalex.org/W2887417925","https://openalex.org/W2896457183","https://openalex.org/W2949161920","https://openalex.org/W3046407074","https://openalex.org/W3046440678","https://openalex.org/W3047002910","https://openalex.org/W3091097978","https://openalex.org/W3153854431","https://openalex.org/W3154219392","https://openalex.org/W4200023416","https://openalex.org/W4225586951","https://openalex.org/W4225673079","https://openalex.org/W4226479682","https://openalex.org/W4249923717","https://openalex.org/W4288083766","https://openalex.org/W4289401659","https://openalex.org/W4295312788","https://openalex.org/W4321484191","https://openalex.org/W6633802082","https://openalex.org/W6755207826","https://openalex.org/W6760703128","https://openalex.org/W6766978945","https://openalex.org/W6794216301","https://openalex.org/W6804847758","https://openalex.org/W6810117058","https://openalex.org/W6810902742","https://openalex.org/W6811928498"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W2358668433","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2997094352"],"abstract_inverted_index":{"The":[0],"surging":[1],"scale":[2],"of":[3,73,120,173],"distributed":[4],"training":[5],"(DT)":[6],"incurs":[7],"significant":[8],"communication":[9,83],"overhead":[10],"in":[11,76],"datacenters,":[12],"while":[13,63],"a":[14,118,170],"promising":[15],"solution":[16],"is":[17,129],"in-network":[18,100],"aggregation":[19,31],"(INA).":[20],"It":[21],"leverages":[22],"programmable":[23],"switches":[24,61,104,177],"(e.g.,":[25,81],"Intel":[26,175],"Tofino":[27,176],"switches)":[28],"for":[29,52,69,131],"gradient":[30,96],"to":[32,37,46,58,135,194],"accelerate":[33],"the":[34,48,70,92,115,159,189,195],"DT.":[35],"Due":[36],"switches'":[38],"limited":[39],"on-chip":[40],"memory":[41,49],"size,":[42],"existing":[43,77],"solutions":[44,78],"try":[45],"design":[47,149],"sharing":[50],"mechanism":[51,55],"INA.":[53],"This":[54],"requires":[56],"gradients":[57,126],"arrive":[59],"at":[60],"synchronously,":[62],"network":[64],"dynamics":[65],"make":[66],"it":[67],"common":[68],"asynchronous":[71],"arrival":[72],"gradients,":[74],"resulting":[75],"being":[79],"inefficient":[80],"massive":[82],"overhead).":[84],"To":[85,145],"address":[86],"this":[87,146],"issue,":[88],"we":[89,148],"propose":[90],"GOAT,":[91],"first-of-its-kind":[93],"work":[94],"on":[95,169],"scheduling":[97],"with":[98],"collaborative":[99],"aggregation,":[101],"so":[102],"that":[103,184],"can":[105,186],"efficiently":[106],"aggregate":[107],"asynchronously":[108],"arriving":[109],"gradients.":[110,144],"Specifically,":[111],"GOAT":[112,164,185],"first":[113],"partitions":[114],"model":[116],"into":[117],"set":[119],"sub-models,":[121],"then":[122],"decides":[123],"which":[124,136],"sub-model":[125,143],"each":[127,138],"switch":[128,137],"responsible":[130],"aggregating":[132],"exclusively":[133],"and":[134,156,165,178],"worker":[139],"should":[140],"send":[141],"its":[142,167],"end,":[147],"an":[150],"efficient":[151],"knapsack-based":[152],"randomized":[153],"rounding":[154],"algorithm":[155],"formally":[157],"analyze":[158],"approximation":[160],"performance.":[161],"We":[162],"implement":[163],"evaluate":[166],"performance":[168],"testbed":[171],"consisting":[172],"3":[174],"9":[179],"servers.":[180],"Experimental":[181],"results":[182],"show":[183],"speed":[187],"up":[188],"DT":[190],"by":[191],"1.5\u00d7":[192],"compared":[193],"state-of-the-art":[196],"solutions.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}