{"id":"https://openalex.org/W4394892714","doi":"https://doi.org/10.1145/3617232.3624863","title":"Training Job Placement in Clusters with Statistical In-Network Aggregation","display_name":"Training Job Placement in Clusters with Statistical In-Network Aggregation","publication_year":2024,"publication_date":"2024-04-17","ids":{"openalex":"https://openalex.org/W4394892714","doi":"https://doi.org/10.1145/3617232.3624863"},"language":"en","primary_location":{"id":"doi:10.1145/3617232.3624863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617232.3624863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617232.3624863","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3617232.3624863","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083860768","display_name":"Bohan Zhao","orcid":"https://orcid.org/0000-0002-3722-8493"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Zhao","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3722-8493","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095746713","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-9271-0223"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["Tsinghua University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9271-0223","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026622212","display_name":"Shuo Liu","orcid":"https://orcid.org/0000-0002-3546-4070"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Liu","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3546-4070","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Beijing, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102957353","display_name":"Yang Tian","orcid":"https://orcid.org/0000-0002-2492-6719"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Tian","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2492-6719","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Beijing, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5095746716","display_name":"Qiaoling Wang","orcid":"https://orcid.org/0000-0001-5788-6082"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaoling Wang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5788-6082","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Beijing, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031365162","display_name":"Wenfei Wu","orcid":"https://orcid.org/0000-0002-1357-3137"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenfei Wu","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1357-3137","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"420","last_page":"434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9986000061035156,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9969000220298767,"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":0.8004716634750366},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.6746611595153809},{"id":"https://openalex.org/keywords/statistical-time-division-multiplexing","display_name":"Statistical time division multiplexing","score":0.5263986587524414},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5255604982376099},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4977317154407501},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48814496397972107},{"id":"https://openalex.org/keywords/multiplexing","display_name":"Multiplexing","score":0.36264997720718384},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3460693657398224},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21519625186920166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004716634750366},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6746611595153809},{"id":"https://openalex.org/C173512123","wikidata":"https://www.wikidata.org/wiki/Q5978010","display_name":"Statistical time division multiplexing","level":3,"score":0.5263986587524414},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5255604982376099},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4977317154407501},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48814496397972107},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.36264997720718384},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3460693657398224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21519625186920166},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3617232.3624863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617232.3624863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617232.3624863","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3617232.3624863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617232.3624863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617232.3624863","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394892714.pdf","grobid_xml":"https://content.openalex.org/works/W4394892714.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1536639265","https://openalex.org/W2042876290","https://openalex.org/W2060393849","https://openalex.org/W2118809092","https://openalex.org/W2131613942","https://openalex.org/W2143295630","https://openalex.org/W2163278024","https://openalex.org/W2164740236","https://openalex.org/W2170475648","https://openalex.org/W2609354095","https://openalex.org/W2734941459","https://openalex.org/W2769986458","https://openalex.org/W2798515322","https://openalex.org/W2919897868","https://openalex.org/W2949161920","https://openalex.org/W2962684017","https://openalex.org/W2962725887","https://openalex.org/W2969388332","https://openalex.org/W2975712713","https://openalex.org/W3043522163","https://openalex.org/W3095429755","https://openalex.org/W3102385572","https://openalex.org/W3137135510","https://openalex.org/W3156353042","https://openalex.org/W3162118826","https://openalex.org/W3206778761","https://openalex.org/W4242634435","https://openalex.org/W4318540560","https://openalex.org/W4321484191","https://openalex.org/W4327911839"],"related_works":["https://openalex.org/W3030636240","https://openalex.org/W431360389","https://openalex.org/W2063698109","https://openalex.org/W2166601301","https://openalex.org/W1538654733","https://openalex.org/W1580283584","https://openalex.org/W2361869782","https://openalex.org/W2045290981","https://openalex.org/W2044046257","https://openalex.org/W2388548392"],"abstract_inverted_index":{"In-Network":[0],"Aggregation":[1],"(INA)":[2],"offloads":[3],"the":[4,15,46,72,87,102,106,132,136,143],"gradient":[5],"aggregation":[6],"in":[7,23,34,52,105,155],"distributed":[8],"training":[9],"(DT)":[10],"onto":[11],"programmable":[12],"switches,":[13],"where":[14],"switch":[16,35],"memory":[17,36],"could":[18],"be":[19],"allocated":[20],"to":[21,70,100,113,126],"jobs":[22,85],"either":[24],"synchronous":[25],"or":[26],"statistical":[27,66],"multiplexing":[28],"mode.":[29],"Statistical":[30],"INA":[31],"has":[32],"advantages":[33],"utilization,":[37],"control-plane":[38],"simplicity,":[39],"and":[40,77,83,118,120,142],"management":[41],"safety,":[42],"but":[43],"it":[44],"faces":[45],"problem":[47],"of":[48,74,140,157],"cross-layer":[49],"resource":[50],"efficiency":[51],"job":[53,59,150,159],"placement.":[54],"This":[55],"paper":[56],"presents":[57],"a":[58,91,95,122],"placement":[60,151],"system":[61],"NetPack":[62,80,93,141,147],"for":[63,129,135],"clusters":[64],"with":[65,131],"INA,":[67],"which":[68],"aims":[69],"maximize":[71],"utilization":[73],"both":[75],"computation":[76],"network":[78],"resources.":[79],"periodically":[81],"batches":[82],"places":[84],"into":[86],"cluster.":[88],"When":[89],"placing":[90],"job,":[92],"runs":[94,121],"steady":[96],"state":[97],"estimation":[98],"algorithm":[99,125],"acquire":[101],"available":[103,115],"resources":[104,116],"cluster,":[107],"heuristically":[108],"values":[109],"each":[110],"server":[111],"according":[112],"its":[114],"(GPU":[117],"bandwidth),":[119],"dynamic":[123],"programming":[124],"efficiently":[127],"search":[128],"servers":[130],"highest":[133],"value":[134],"job.":[137],"Our":[138],"prototype":[139],"experiments":[144],"demonstrate":[145],"that":[146],"outperforms":[148],"prior":[149],"methods":[152],"by":[153],"45%":[154],"terms":[156],"average":[158],"completion":[160],"time":[161],"on":[162],"production":[163],"traces.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
