{"id":"https://openalex.org/W4416298027","doi":"https://doi.org/10.1145/3772356.3772387","title":"JEEVES: The Valet Who Masters the Art of Cross-DC Training Scheduling","display_name":"JEEVES: The Valet Who Masters the Art of Cross-DC Training Scheduling","publication_year":2025,"publication_date":"2025-11-17","ids":{"openalex":"https://openalex.org/W4416298027","doi":"https://doi.org/10.1145/3772356.3772387"},"language":null,"primary_location":{"id":"doi:10.1145/3772356.3772387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772356.3772387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3772356.3772387","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 24th ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3772356.3772387","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111601575","display_name":"Haotian Deng","orcid":"https://orcid.org/0009-0006-7490-5568"},"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":true,"raw_author_name":"Haotian Deng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7490-5568","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086938558","display_name":"Xiao-Rui Song","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuebin Song","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-2773-3742","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031176052","display_name":"Menghao Zhang","orcid":"https://orcid.org/0000-0001-5274-5512"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghao Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5274-5512","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101579014","display_name":"Yuan Yang","orcid":"https://orcid.org/0000-0002-3481-8447"},"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":"Yuan Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3481-8447","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100771111","display_name":"Mingwei Xu","orcid":"https://orcid.org/0000-0002-4847-4585"},"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":"Mingwei Xu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4847-4585","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111601575"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46852741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.8003000020980835,"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":0.8003000020980835,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.09830000251531601,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.0203000009059906,"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/scheduling","display_name":"Scheduling (production processes)","score":0.679099977016449},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5896999835968018},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.5537999868392944},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5371000170707703},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.47920000553131104},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4169999957084656},{"id":"https://openalex.org/keywords/data-center","display_name":"Data center","score":0.383899986743927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.679099977016449},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.47920000553131104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C153740404","wikidata":"https://www.wikidata.org/wiki/Q671224","display_name":"Data center","level":2,"score":0.383899986743927},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.263700008392334}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3772356.3772387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772356.3772387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3772356.3772387","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 24th ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3772356.3772387","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772356.3772387","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3772356.3772387","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 24th ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5624481092","display_name":null,"funder_award_id":"2022YFB2901300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7291191679","display_name":null,"funder_award_id":"62402025","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/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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416298027.pdf","grobid_xml":"https://content.openalex.org/works/W4416298027.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W3046364876","https://openalex.org/W3081168214","https://openalex.org/W3132107458","https://openalex.org/W3204998121","https://openalex.org/W3206832494","https://openalex.org/W4386348101","https://openalex.org/W4394945032"],"related_works":[],"abstract_inverted_index":{"As":[0],"model":[1],"sizes":[2],"continue":[3],"to":[4,63,104],"grow":[5],"and":[6,42,82,84,91],"the":[7,58,73],"capacity":[8],"of":[9,45,80],"a":[10,54,77,108],"single":[11],"data":[12,20],"center":[13],"becomes":[14],"insufficient,":[15],"training":[16,107],"models":[17],"across":[18,61],"multiple":[19],"centers":[21],"efficiently":[22],"is":[23],"becoming":[24],"increasingly":[25],"important.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,51],"first":[31],"show":[32,96],"that":[33,56,72,97],"existing":[34],"parallelism":[35,60],"strategies":[36],"perform":[37],"poorly":[38],"under":[39,67],"limited":[40],"bandwidth":[41],"high":[43],"latency":[44],"cross-DC":[46],"links.":[47],"To":[48],"address":[49],"this,":[50],"propose":[52,85],"JEEVES,":[53],"framework":[55],"extends":[57],"pipeline":[59],"DCs":[62],"minimize":[64],"iteration":[65,100],"time":[66,101],"memory":[68],"constraints.":[69],"We":[70],"identify":[71],"key":[74],"lies":[75],"in":[76],"good":[78],"schedule":[79],"computation":[81],"communication,":[83],"communication-aware":[86],"schedule,":[87],"memory-aware":[88],"stage":[89],"division":[90],"inter-replica":[92],"coordinated":[93],"schedule.":[94],"Simulations":[95],"JEEVES":[98],"improves":[99],"by":[102],"up":[103],"43%":[105],"when":[106],"175B-parameter":[109],"model.":[110]},"counts_by_year":[],"updated_date":"2026-03-09T07:00:12.390032","created_date":"2025-11-17T00:00:00"}