{"id":"https://openalex.org/W4308995136","doi":"https://doi.org/10.1145/3563766.3564096","title":"Efficient flow scheduling in distributed deep learning training with echelon formation","display_name":"Efficient flow scheduling in distributed deep learning training with echelon formation","publication_year":2022,"publication_date":"2022-11-14","ids":{"openalex":"https://openalex.org/W4308995136","doi":"https://doi.org/10.1145/3563766.3564096"},"language":"en","primary_location":{"id":"doi:10.1145/3563766.3564096","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3563766.3564096","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3563766.3564096","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3563766.3564096","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638027","display_name":"Rui Pan","orcid":"https://orcid.org/0000-0002-6973-3259"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Pan","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048356019","display_name":"Yiming Lei","orcid":"https://orcid.org/0000-0002-5344-4479"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yiming Lei","raw_affiliation_strings":["Max Planck Institute for Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100708117","display_name":"Jialong Li","orcid":"https://orcid.org/0000-0003-3416-5551"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jialong Li","raw_affiliation_strings":["Max Planck Institute for Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028856593","display_name":"Zhiqiang Xie","orcid":"https://orcid.org/0000-0001-7422-1568"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiqiang Xie","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002684888","display_name":"Binhang Yuan","orcid":"https://orcid.org/0000-0002-3188-2769"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Binhang Yuan","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111938680","display_name":"Yiting Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yiting Xia","raw_affiliation_strings":["Max Planck Institute for Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2306,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90519757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9991999864578247,"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":0.9991999864578247,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9976999759674072,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8356437683105469},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7019679546356201},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.6865283250808716},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6592740416526794},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.6116628646850586},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5746766328811646},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5745029449462891},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5380781292915344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5367124676704407},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37943992018699646},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15363895893096924},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09305953979492188},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0928928554058075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8356437683105469},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7019679546356201},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.6865283250808716},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6592740416526794},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.6116628646850586},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5746766328811646},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5745029449462891},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5380781292915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367124676704407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37943992018699646},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15363895893096924},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09305953979492188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0928928554058075},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3563766.3564096","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3563766.3564096","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3563766.3564096","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"},{"id":"pmh:oai:www.research-collection.ethz.ch:20.500.11850/591849","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11850/591849","pdf_url":"http://hdl.handle.net/20.500.11850/591849","source":{"id":"https://openalex.org/S4306402302","display_name":"Repository for Publications and Research Data (ETH Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I35440088","host_organization_name":"ETH Zurich","host_organization_lineage":["https://openalex.org/I35440088"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"HotNets '22: Proceedings of the 21st ACM Workshop on Hot Topics in Networks","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-128656","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-128656","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"},{"id":"doi:10.3929/ethz-b-000591849","is_oa":true,"landing_page_url":"https://doi.org/10.3929/ethz-b-000591849","pdf_url":null,"source":{"id":"https://openalex.org/S7407051236","display_name":"ETH Z\u00fcrich Research Collection","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1145/3563766.3564096","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3563766.3564096","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3563766.3564096","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Workshop on Hot Topics in Networks","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308995136.pdf","grobid_xml":"https://content.openalex.org/works/W4308995136.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W292761019","https://openalex.org/W1545728916","https://openalex.org/W2013932952","https://openalex.org/W2060393849","https://openalex.org/W2100830825","https://openalex.org/W2149939304","https://openalex.org/W2170616854","https://openalex.org/W2173213060","https://openalex.org/W2488801318","https://openalex.org/W2594041104","https://openalex.org/W2734941459","https://openalex.org/W2780624097","https://openalex.org/W2781241399","https://openalex.org/W2789335636","https://openalex.org/W2824896242","https://openalex.org/W2894576937","https://openalex.org/W2944793600","https://openalex.org/W2952435244","https://openalex.org/W2969388332","https://openalex.org/W2975712713","https://openalex.org/W2981114289","https://openalex.org/W3006487403","https://openalex.org/W3038098022","https://openalex.org/W3044837714","https://openalex.org/W3047537431","https://openalex.org/W3081168214","https://openalex.org/W3086105743","https://openalex.org/W3095429755","https://openalex.org/W3124352525","https://openalex.org/W3129831491","https://openalex.org/W3162070257","https://openalex.org/W3202009823","https://openalex.org/W3204998121","https://openalex.org/W3207941295","https://openalex.org/W4226057994","https://openalex.org/W4232284301","https://openalex.org/W4288093768","https://openalex.org/W4288357791","https://openalex.org/W6769475105"],"related_works":["https://openalex.org/W2378994405","https://openalex.org/W2385974820","https://openalex.org/W2373478030","https://openalex.org/W2378679551","https://openalex.org/W3149739944","https://openalex.org/W2964266708","https://openalex.org/W4299685261","https://openalex.org/W2797225766","https://openalex.org/W4310562451","https://openalex.org/W4390872497"],"abstract_inverted_index":{"This":[0],"paper":[1],"discusses":[2],"why":[3],"flow":[4,89],"scheduling":[5,117],"does":[6],"not":[7],"apply":[8],"to":[9,21,74,87],"distributed":[10,55],"deep":[11],"learning":[12],"training":[13,52,56,82,97],"and":[14,84,107],"presents":[15],"EchelonFlow,":[16],"the":[17,23,28,38,43,76,102,105,112],"first":[18],"network":[19],"abstraction":[20],"bridge":[22],"gap.":[24],"EchelonFlow":[25,86,100,116],"deviates":[26],"from":[27],"common":[29],"belief":[30],"that":[31,54],"semantically":[32],"related":[33],"flows":[34],"should":[35],"finish":[36,90],"at":[37,66],"same":[39],"time.":[40],"We":[41,69],"reached":[42],"key":[44],"observation,":[45],"after":[46],"extensive":[47],"workflow":[48],"analysis":[49],"of":[50,95,104,114],"diverse":[51],"paradigms,":[53,83],"jobs":[57],"observe":[58],"strict":[59],"computation":[60,79],"patterns,":[61],"which":[62],"may":[63],"consume":[64],"data":[65],"different":[67,78],"times.":[68],"devise":[70],"a":[71],"generic":[72],"method":[73],"model":[75],"drastically":[77],"patterns":[80],"across":[81],"formulate":[85],"regulate":[88],"times":[91],"accordingly.":[92],"Case":[93],"studies":[94],"mainstream":[96],"paradigms":[98],"under":[99],"demonstrate":[101],"expressiveness":[103],"abstraction,":[106],"our":[108],"system":[109],"sketch":[110],"suggests":[111],"feasibility":[113],"an":[115],"system.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}