{"id":"https://openalex.org/W4414170548","doi":"https://doi.org/10.1109/iwqos65803.2025.11143475","title":"Flux: Fine-Grained Communication Scheduling for Distributed Training in Multi-Tenant AI Clusters","display_name":"Flux: Fine-Grained Communication Scheduling for Distributed Training in Multi-Tenant AI Clusters","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414170548","doi":"https://doi.org/10.1109/iwqos65803.2025.11143475"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-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/A5021471392","display_name":"Jiashuo Lin","orcid":"https://orcid.org/0000-0003-4074-7291"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiashuo Lin","raw_affiliation_strings":["Southern University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101744560","display_name":"Xingbo Feng","orcid":"https://orcid.org/0000-0002-8141-3709"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingbo Feng","raw_affiliation_strings":["Southern University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056925197","display_name":"Huilin Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanrui Qi","raw_affiliation_strings":["Southern University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092186471","display_name":"Yan Liu","orcid":"https://orcid.org/0009-0006-6266-4218"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Liu","raw_affiliation_strings":["Southern University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086746907","display_name":"Chenxi Ling","orcid":null},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxi Ling","raw_affiliation_strings":["Southern University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101455932","display_name":"Bo Tang","orcid":"https://orcid.org/0000-0002-6035-5167"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Tang","raw_affiliation_strings":["Southern University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364961","display_name":"Yi Wang","orcid":"https://orcid.org/0000-0002-5773-3817"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wang","raw_affiliation_strings":["Southern University of Science and Technology,China"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology,China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114206912","display_name":"Xiaofeng Tao","orcid":null},"institutions":[{"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":"Xiaofeng Tao","raw_affiliation_strings":["Pengcheng Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100637377","display_name":"Weichao Li","orcid":null},"institutions":[{"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":"Weichao Li","raw_affiliation_strings":["Pengcheng Laboratory,China"],"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory,China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5021471392"],"corresponding_institution_ids":["https://openalex.org/I3045169105"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27484474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9943000078201294,"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":0.9943000078201294,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9782000184059143,"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":0.9764999747276306,"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/scheduling","display_name":"Scheduling (production processes)","score":0.7408999800682068},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6402999758720398},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5400000214576721},{"id":"https://openalex.org/keywords/fixed-priority-pre-emptive-scheduling","display_name":"Fixed-priority pre-emptive scheduling","score":0.4921000003814697},{"id":"https://openalex.org/keywords/fair-share-scheduling","display_name":"Fair-share scheduling","score":0.4422000050544739},{"id":"https://openalex.org/keywords/two-level-scheduling","display_name":"Two-level scheduling","score":0.4309999942779541},{"id":"https://openalex.org/keywords/dynamic-priority-scheduling","display_name":"Dynamic priority scheduling","score":0.35269999504089355},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.32519999146461487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014000058174133},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.7408999800682068},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6402999758720398},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6292999982833862},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C122141398","wikidata":"https://www.wikidata.org/wiki/Q5456330","display_name":"Fixed-priority pre-emptive scheduling","level":5,"score":0.4921000003814697},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.4422000050544739},{"id":"https://openalex.org/C119948110","wikidata":"https://www.wikidata.org/wiki/Q7858726","display_name":"Two-level scheduling","level":4,"score":0.4309999942779541},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.33550000190734863},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C111873713","wikidata":"https://www.wikidata.org/wiki/Q1641413","display_name":"Job scheduler","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C69016650","wikidata":"https://www.wikidata.org/wiki/Q1364211","display_name":"Multitenancy","level":5,"score":0.3212999999523163},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C127456818","wikidata":"https://www.wikidata.org/wiki/Q238879","display_name":"Rate-monotonic scheduling","level":4,"score":0.2818000018596649},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25060001015663147},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143475","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3213010520","display_name":null,"funder_award_id":"2024A0101010001","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2975712713","https://openalex.org/W4300973219","https://openalex.org/W4385966327","https://openalex.org/W4401176820"],"related_works":[],"abstract_inverted_index":{"Communication":[0],"overhead":[1],"is":[2],"a":[3,34],"major":[4],"bottleneck":[5],"in":[6,11,76],"distributed":[7],"AI":[8,78],"training,":[9],"particularly":[10],"multi-tenant":[12],"environments,":[13],"limiting":[14],"GPU":[15,55],"utilization.":[16],"Existing":[17],"job-level":[18,65],"scheduling":[19,75],"methods":[20],"fail":[21],"to":[22,59,63],"address":[23],"the":[24,69],"varying":[25],"urgency":[26],"of":[27,72],"individual":[28],"communication":[29,40,74],"operations.":[30],"We":[31],"propose":[32],"Flux,":[33],"novel":[35],"fine-grained":[36,73],"scheduler":[37],"that":[38],"prioritizes":[39],"operations":[41],"based":[42],"on":[43],"their":[44],"Urgency":[45],"Score":[46],"and":[47],"job":[48],"intensity.":[49],"Our":[50],"evaluation":[51],"shows":[52],"Flux":[53],"improves":[54],"utilization":[56],"by":[57],"up":[58],"10":[60],"%":[61],"compared":[62],"state-of-the-art":[64],"algorithms.":[66],"This":[67],"demonstrates":[68],"significant":[70],"advantage":[71],"multitenant":[77],"clusters.":[79]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
