{"id":"https://openalex.org/W4321484191","doi":"https://doi.org/10.1109/tnet.2023.3244794","title":"GRID: Gradient Routing With In-Network Aggregation for Distributed Training","display_name":"GRID: Gradient Routing With In-Network Aggregation for Distributed Training","publication_year":2023,"publication_date":"2023-02-22","ids":{"openalex":"https://openalex.org/W4321484191","doi":"https://doi.org/10.1109/tnet.2023.3244794"},"language":"en","primary_location":{"id":"doi:10.1109/tnet.2023.3244794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnet.2023.3244794","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, China","Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, 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, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, 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, Hefei, China","Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, 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, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, 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, Hefei, China","Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, 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, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063764101","display_name":"Changbo Wu","orcid":"https://orcid.org/0009-0004-9285-0594"},"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":"Changbo Wu","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, China","institution_ids":[]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.6959,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.97417331,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":"5","first_page":"2267","last_page":"2280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9944999814033508,"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":0.9944999814033508,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9934999942779541,"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":0.993399977684021,"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":0.8115330934524536},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6315736770629883},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.527912437915802},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5012848377227783},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.4710122346878052},{"id":"https://openalex.org/keywords/multipath-routing","display_name":"Multipath routing","score":0.45289507508277893},{"id":"https://openalex.org/keywords/routing-table","display_name":"Routing table","score":0.4472365379333496},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.44214388728141785},{"id":"https://openalex.org/keywords/static-routing","display_name":"Static routing","score":0.441049188375473},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.42258748412132263},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.392447829246521},{"id":"https://openalex.org/keywords/routing-protocol","display_name":"Routing protocol","score":0.2008417546749115},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.15788957476615906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115330934524536},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6315736770629883},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.527912437915802},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5012848377227783},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.4710122346878052},{"id":"https://openalex.org/C76522221","wikidata":"https://www.wikidata.org/wiki/Q5035396","display_name":"Multipath routing","level":5,"score":0.45289507508277893},{"id":"https://openalex.org/C184896649","wikidata":"https://www.wikidata.org/wiki/Q290066","display_name":"Routing table","level":4,"score":0.4472365379333496},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.44214388728141785},{"id":"https://openalex.org/C204948658","wikidata":"https://www.wikidata.org/wiki/Q1119410","display_name":"Static routing","level":4,"score":0.441049188375473},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.42258748412132263},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.392447829246521},{"id":"https://openalex.org/C104954878","wikidata":"https://www.wikidata.org/wiki/Q1648707","display_name":"Routing protocol","level":3,"score":0.2008417546749115},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.15788957476615906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnet.2023.3244794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnet.2023.3244794","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/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/G645416012","display_name":null,"funder_award_id":"62132019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":96,"referenced_works":["https://openalex.org/W1536639265","https://openalex.org/W1686810756","https://openalex.org/W1994926493","https://openalex.org/W2001174522","https://openalex.org/W2057332538","https://openalex.org/W2060393849","https://openalex.org/W2079735306","https://openalex.org/W2096655151","https://openalex.org/W2113487548","https://openalex.org/W2117539524","https://openalex.org/W2130531694","https://openalex.org/W2138302120","https://openalex.org/W2143295630","https://openalex.org/W2166706236","https://openalex.org/W2168231600","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2463357960","https://openalex.org/W2524428287","https://openalex.org/W2606891064","https://openalex.org/W2617766261","https://openalex.org/W2739273093","https://openalex.org/W2769644379","https://openalex.org/W2769986458","https://openalex.org/W2774000609","https://openalex.org/W2896457183","https://openalex.org/W2899071864","https://openalex.org/W2906731962","https://openalex.org/W2923285122","https://openalex.org/W2946900926","https://openalex.org/W2949161920","https://openalex.org/W2955762123","https://openalex.org/W2962700998","https://openalex.org/W2963334472","https://openalex.org/W2963773265","https://openalex.org/W2969517360","https://openalex.org/W2975712713","https://openalex.org/W2981114289","https://openalex.org/W3012220622","https://openalex.org/W3015585426","https://openalex.org/W3037047862","https://openalex.org/W3047002910","https://openalex.org/W3091097978","https://openalex.org/W3093999374","https://openalex.org/W3096403968","https://openalex.org/W3101036738","https://openalex.org/W3124352525","https://openalex.org/W3137135510","https://openalex.org/W3153854431","https://openalex.org/W3154219392","https://openalex.org/W3159145702","https://openalex.org/W3187356235","https://openalex.org/W3188706325","https://openalex.org/W3190458349","https://openalex.org/W3193181769","https://openalex.org/W3212066104","https://openalex.org/W3216547135","https://openalex.org/W4236362309","https://openalex.org/W4242634435","https://openalex.org/W4249923717","https://openalex.org/W4288093768","https://openalex.org/W4288277757","https://openalex.org/W4288357791","https://openalex.org/W4289401659","https://openalex.org/W4295312788","https://openalex.org/W4301239768","https://openalex.org/W6631896231","https://openalex.org/W6637373629","https://openalex.org/W6680748266","https://openalex.org/W6684249991","https://openalex.org/W6684859321","https://openalex.org/W6686164453","https://openalex.org/W6727208969","https://openalex.org/W6738460352","https://openalex.org/W6746200960","https://openalex.org/W6746839373","https://openalex.org/W6748645090","https://openalex.org/W6751961731","https://openalex.org/W6754143808","https://openalex.org/W6754187583","https://openalex.org/W6754818105","https://openalex.org/W6755207826","https://openalex.org/W6755251367","https://openalex.org/W6756009870","https://openalex.org/W6757449384","https://openalex.org/W6760703128","https://openalex.org/W6762211661","https://openalex.org/W6763138067","https://openalex.org/W6765375071","https://openalex.org/W6766633873","https://openalex.org/W6766978945","https://openalex.org/W6769475105","https://openalex.org/W6775649616","https://openalex.org/W6784425352","https://openalex.org/W6792106764","https://openalex.org/W6794216301"],"related_works":["https://openalex.org/W2139584334","https://openalex.org/W757657516","https://openalex.org/W2539097916","https://openalex.org/W2944616377","https://openalex.org/W2918996422","https://openalex.org/W3127002380","https://openalex.org/W2889464401","https://openalex.org/W4377970799","https://openalex.org/W2168517869","https://openalex.org/W2251995179"],"abstract_inverted_index":{"As":[0],"the":[1,19,33,40,54,98,111,128,132,142,185],"scale":[2],"of":[3,144,161,173],"distributed":[4,193],"training":[5,34,194],"increases,":[6],"it":[7],"brings":[8],"huge":[9],"communication":[10,20,26,88,186],"overhead":[11],"in":[12,57,62,83],"clusters.":[13],"Some":[14],"works":[15],"try":[16],"to":[17,52],"reduce":[18,39,184],"cost":[21],"through":[22,76],"gradient":[23,118],"compression":[24],"or":[25,36],"scheduling.":[27],"However,":[28,69],"these":[29],"methods":[30],"either":[31],"downgrade":[32],"accuracy":[35],"do":[37],"not":[38],"total":[41],"transmission":[42],"amount.":[43],"One":[44],"promising":[45],"approach,":[46],"called":[47],"in-network":[48,74,137],"aggregation,":[49],"is":[50],"proposed":[51],"mitigate":[53],"bandwidth":[55],"bottleneck":[56],"clusters":[58],"by":[59,139,188,195],"aggregating":[60],"gradients":[61],"programmable":[63,147],"hardware":[64],"(e.g.,":[65],"Intel":[66,163],"Tofino":[67,164],"switches).":[68],"existing":[70],"solutions":[71],"mainly":[72],"implement":[73,150],"aggregation":[75,138],"fixed":[77],"(or":[78],"default)":[79],"routing":[80,119],"paths,":[81],"resulting":[82],"load":[84],"imbalancing":[85],"and":[86,125,146,152,166,176,190],"long":[87],"time.":[89],"To":[90],"deal":[91],"with":[92,104,198],"this":[93],"issue,":[94],"we":[95,114,135,179],"propose":[96],"GRID,":[97],"first-of-its-kind":[99],"work":[100],"on":[101,122,156],"Gradient":[102],"Routing":[103],"In-network":[105],"Aggregation":[106],"for":[107],"Distributed":[108],"Training.":[109],"In":[110,131],"control":[112],"plane,":[113,134],"present":[115],"an":[116],"efficient":[117],"algorithm":[120],"based":[121],"randomized":[123],"rounding":[124],"formally":[126],"analyze":[127],"approximation":[129],"performance.":[130],"data":[133],"realize":[136],"carefully":[140],"designing":[141],"logic":[143],"workers":[145],"switches.":[148],"We":[149],"GRID":[151,182],"evaluate":[153],"its":[154],"performance":[155],"a":[157,171],"small-scale":[158],"testbed":[159,174],"consisting":[160],"3":[162],"switches":[165],"9":[167],"commodity":[168],"servers.":[169],"With":[170],"combination":[172],"experiments":[175],"large-scale":[177],"simulations,":[178],"show":[180],"that":[181],"can":[183],"time":[187],"38.4%\u201360.1%":[189],"speed":[191],"up":[192],"17.4%\u201352.7%":[196],"compared":[197],"state-of-the-art":[199],"solutions.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":8}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
