{"id":"https://openalex.org/W4396240007","doi":"https://doi.org/10.1109/tnet.2024.3387948","title":"Accelerating Distributed Training With Collaborative In-Network Aggregation","display_name":"Accelerating Distributed Training With Collaborative In-Network Aggregation","publication_year":2024,"publication_date":"2024-04-29","ids":{"openalex":"https://openalex.org/W4396240007","doi":"https://doi.org/10.1109/tnet.2024.3387948"},"language":"en","primary_location":{"id":"doi:10.1109/tnet.2024.3387948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnet.2024.3387948","pdf_url":null,"source":{"id":"https://openalex.org/S62238642","display_name":"IEEE/ACM Transactions on Networking","issn_l":"1063-6692","issn":["1063-6692","1558-2566"],"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/ACM Transactions on Networking","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/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, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-4222-1971","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-3831-4577","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-1311-8908","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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":["Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Johns Hopkins University, Baltimore, MD, 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, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"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":["Department of Computer Science, Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA, 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":1.7045,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84513883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"32","issue":"4","first_page":"3437","last_page":"3452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9975000023841858,"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":0.9975000023841858,"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.994700014591217,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/training","display_name":"Training (meteorology)","score":0.7168638110160828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5734164714813232},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07034638524055481}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7168638110160828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5734164714813232},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07034638524055481},{"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/tnet.2024.3387948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnet.2024.3387948","pdf_url":null,"source":{"id":"https://openalex.org/S62238642","display_name":"IEEE/ACM Transactions on Networking","issn_l":"1063-6692","issn":["1063-6692","1558-2566"],"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/ACM Transactions on Networking","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1458367098","display_name":null,"funder_award_id":"62372426","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1745555229","display_name":null,"funder_award_id":"2023481","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"},{"id":"https://openalex.org/G7563642939","display_name":null,"funder_award_id":"BK20210121","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7748147380","display_name":null,"funder_award_id":"62102392","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/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","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":63,"referenced_works":["https://openalex.org/W1563795667","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/W2751108192","https://openalex.org/W2768149277","https://openalex.org/W2771813345","https://openalex.org/W2887417925","https://openalex.org/W2896457183","https://openalex.org/W2902423855","https://openalex.org/W2960944858","https://openalex.org/W2962725887","https://openalex.org/W2963334472","https://openalex.org/W3012220622","https://openalex.org/W3014418536","https://openalex.org/W3015585426","https://openalex.org/W3046407074","https://openalex.org/W3046440678","https://openalex.org/W3047002910","https://openalex.org/W3047565185","https://openalex.org/W3091097978","https://openalex.org/W3155611867","https://openalex.org/W3212066104","https://openalex.org/W4200023416","https://openalex.org/W4225586951","https://openalex.org/W4226479682","https://openalex.org/W4236362309","https://openalex.org/W4242634435","https://openalex.org/W4249923717","https://openalex.org/W4256049924","https://openalex.org/W4285302300","https://openalex.org/W4288083766","https://openalex.org/W4289401659","https://openalex.org/W4321484191","https://openalex.org/W4327911839","https://openalex.org/W4328030459","https://openalex.org/W4385357021","https://openalex.org/W4389989295","https://openalex.org/W4391164333","https://openalex.org/W4401352466","https://openalex.org/W6633802082","https://openalex.org/W6684249991","https://openalex.org/W6738460352","https://openalex.org/W6749257597","https://openalex.org/W6751961731","https://openalex.org/W6754143808","https://openalex.org/W6754187583","https://openalex.org/W6755207826","https://openalex.org/W6755251367","https://openalex.org/W6756009870","https://openalex.org/W6760703128","https://openalex.org/W6763138067","https://openalex.org/W6763300512","https://openalex.org/W6766633873","https://openalex.org/W6766978945","https://openalex.org/W6775649616","https://openalex.org/W6794216301","https://openalex.org/W6810117058","https://openalex.org/W6810902742","https://openalex.org/W6811928498"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"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":[32,37,46,58,135,201],"accelerate":[33],"DT":[34,190],"tasks.":[35],"Due":[36],"switches\u2019":[38],"limited":[39],"on-chip":[40],"memory":[41,49],"size,":[42],"existing":[43,77],"solutions":[44,78],"try":[45],"design":[47,149],"the":[48,70,92,115,159,189,202],"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],"by":[191],"<inline-formula":[192],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[194],"<tex-math":[195],"notation=\"LaTeX\">$1.5":[196],"\\times":[197],"$":[198],"</tex-math></inline-formula>":[199],"compared":[200],"state-of-the-art":[203],"solutions.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}