{"id":"https://openalex.org/W3020638693","doi":"https://doi.org/10.1109/tnsm.2020.2989187","title":"Grouper: Accelerating Hyperparameter Searching in Deep Learning Clusters With Network Scheduling","display_name":"Grouper: Accelerating Hyperparameter Searching in Deep Learning Clusters With Network Scheduling","publication_year":2020,"publication_date":"2020-04-21","ids":{"openalex":"https://openalex.org/W3020638693","doi":"https://doi.org/10.1109/tnsm.2020.2989187","mag":"3020638693"},"language":"en","primary_location":{"id":"doi:10.1109/tnsm.2020.2989187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2020.2989187","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"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 Transactions on Network and Service Management","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/A5020559505","display_name":"Pan Zhou","orcid":"https://orcid.org/0000-0003-3373-728X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":["Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0003-3373-728X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101507232","display_name":"Hongfang Yu","orcid":"https://orcid.org/0000-0002-5219-1780"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfang Yu","raw_affiliation_strings":["Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Science and Technology of China, Chengdu, China","Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5219-1780","affiliations":[{"raw_affiliation_string":"Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053945147","display_name":"Gang Sun","orcid":"https://orcid.org/0000-0002-2448-8915"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Sun","raw_affiliation_strings":["Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2448-8915","affiliations":[{"raw_affiliation_string":"Key Laboratory of Optical Fiber Sensing and Communications, Ministry of Education, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":0.8595,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81710435,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":"17","issue":"3","first_page":"1879","last_page":"1895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9959999918937683,"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":0.8616538047790527},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.7024528980255127},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.665127694606781},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.472398966550827},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.39507198333740234},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.32316166162490845},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3044052720069885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23461157083511353},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2073633074760437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8616538047790527},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7024528980255127},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.665127694606781},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.472398966550827},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39507198333740234},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32316166162490845},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3044052720069885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23461157083511353},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2073633074760437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnsm.2020.2989187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnsm.2020.2989187","pdf_url":null,"source":{"id":"https://openalex.org/S173527311","display_name":"IEEE Transactions on Network and Service Management","issn_l":"1932-4537","issn":["1932-4537","2373-7379"],"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 Transactions on Network and Service Management","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G3544648679","display_name":null,"funder_award_id":"2682019CX61","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4014615201","display_name":null,"funder_award_id":"2019YFB1802800","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6009376170","display_name":null,"funder_award_id":"ZYGX2016J217","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W169464267","https://openalex.org/W1575029535","https://openalex.org/W1960330418","https://openalex.org/W1967183464","https://openalex.org/W1982055457","https://openalex.org/W1998471240","https://openalex.org/W2016002075","https://openalex.org/W2060393849","https://openalex.org/W2075265959","https://openalex.org/W2097998348","https://openalex.org/W2101234009","https://openalex.org/W2121129818","https://openalex.org/W2130531694","https://openalex.org/W2148204686","https://openalex.org/W2149939304","https://openalex.org/W2168427242","https://openalex.org/W2169699126","https://openalex.org/W2186615578","https://openalex.org/W2342784376","https://openalex.org/W2402144811","https://openalex.org/W2556522401","https://openalex.org/W2594041104","https://openalex.org/W2608595939","https://openalex.org/W2617955834","https://openalex.org/W2763132399","https://openalex.org/W2772678505","https://openalex.org/W2789335636","https://openalex.org/W2794670651","https://openalex.org/W2798515322","https://openalex.org/W2809420642","https://openalex.org/W2824896242","https://openalex.org/W2884190946","https://openalex.org/W2895690823","https://openalex.org/W2899071864","https://openalex.org/W2910100551","https://openalex.org/W2919594608","https://openalex.org/W2919897868","https://openalex.org/W2920076211","https://openalex.org/W2921179295","https://openalex.org/W2950082989","https://openalex.org/W2953384591","https://openalex.org/W2962725887","https://openalex.org/W2962746093","https://openalex.org/W2962758826","https://openalex.org/W2963334428","https://openalex.org/W2963403751","https://openalex.org/W2963624798","https://openalex.org/W2963968531","https://openalex.org/W3015516817","https://openalex.org/W3019137413","https://openalex.org/W4213308398","https://openalex.org/W4235670058","https://openalex.org/W4255119735","https://openalex.org/W4289422886","https://openalex.org/W6634542218","https://openalex.org/W6674385629","https://openalex.org/W6675354045","https://openalex.org/W6686509673","https://openalex.org/W6713134421","https://openalex.org/W6730169791","https://openalex.org/W6739693220","https://openalex.org/W6752199355","https://openalex.org/W6755283958","https://openalex.org/W6756009870","https://openalex.org/W6758283263","https://openalex.org/W6759814162"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W4285042611","https://openalex.org/W1509300825","https://openalex.org/W2058728358","https://openalex.org/W4387951187"],"abstract_inverted_index":{"Training":[0],"a":[1,22,45,109,122,147,158],"high-accuracy":[2],"model":[3],"requires":[4,53],"trying":[5],"hundreds":[6],"of":[7,9,24,48,97,111,139,164,175],"configurations":[8,31],"hyperparameters":[10],"to":[11,20,59,77,87,150,161],"search":[12],"for":[13,101,125,154],"the":[14,33,38,61,66,71,92,105,137,173,176],"optimal":[15],"configuration.":[16],"It":[17],"is":[18],"common":[19],"launch":[21],"group":[23],"training":[25],"jobs":[26,39,99],"(named":[27],"cojob)":[28],"with":[29],"different":[30,170],"at":[32,131],"same":[34],"time":[35,57,135],"and":[36,120,166,182,193],"stop":[37],"performing":[40],"worst":[41],"every":[42],"stage":[43,55],"(i.e.,":[44],"certain":[46],"number":[47,110],"iterations).":[49],"Thus":[50],"deep":[51],"learning":[52],"minimizing":[54],"completion":[56,134],"(SCT)":[58],"accelerate":[60],"searching.":[62,141],"To":[63],"quickly":[64],"complete":[65],"stages,":[67],"each":[68],"job":[69],"in":[70,117,172],"cojob":[72],"typically":[73],"uses":[74],"multiple":[75],"GPUs":[76,82],"perform":[78],"distributed":[79],"training.":[80],"The":[81,178],"exchange":[83],"data":[84,95],"per":[85],"iteration":[86],"synchronize":[88],"their":[89],"models":[90],"through":[91],"network.":[93],"However,":[94],"transfers":[96],"DL":[98],"compete":[100],"network":[102,118,189],"bandwidth":[103],"since":[104],"GPU":[106],"cluster":[107],"hosts":[108],"cojobs":[112,165],"from":[113,169],"various":[114],"users,":[115],"resulting":[116],"congestion":[119],"consequently":[121],"large":[123],"SCT":[124,153],"cojobs.":[126,155],"Existing":[127],"flow":[128],"schedulers":[129],"aimed":[130],"reducing":[132],"flow/coflow/job":[133],"mismatch":[136],"requirement":[138],"hyperparameter":[140],"In":[142],"this":[143],"paper,":[144],"we":[145],"implement":[146],"system":[148],"Grouper":[149,156,186],"minimize":[151],"average":[152],"adopts":[157],"well-designed":[159],"algorithm":[160],"permute":[162],"stages":[163,171],"schedules":[167],"flows":[168],"order":[174],"permutation.":[177],"extensive":[179],"testbed":[180],"experiments":[181],"simulations":[183],"show":[184],"that":[185],"outperforms":[187],"advanced":[188],"designs":[190],"Baraat,":[191],"Sincrona,":[192],"per-flow":[194],"fair":[195],"share.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}