{"id":"https://openalex.org/W4401176822","doi":"https://doi.org/10.1145/3651890.3672249","title":"Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem","display_name":"Rethinking Machine Learning Collective Communication as a Multi-Commodity Flow Problem","publication_year":2024,"publication_date":"2024-07-31","ids":{"openalex":"https://openalex.org/W4401176822","doi":"https://doi.org/10.1145/3651890.3672249"},"language":"en","primary_location":{"id":"doi:10.1145/3651890.3672249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651890.3672249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2024 Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033705419","display_name":"Xuting Liu","orcid":"https://orcid.org/0000-0001-8017-6652"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuting Liu","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-8017-6652","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, United States of America","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067060974","display_name":"Behnaz Arzani","orcid":"https://orcid.org/0000-0003-2234-3250"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Behnaz Arzani","raw_affiliation_strings":["Microsoft Research, Redmond, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-2234-3250","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, United States of America","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077950054","display_name":"Siva Kesava Reddy Kakarla","orcid":"https://orcid.org/0009-0006-2694-4685"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siva Kesava Reddy Kakarla","raw_affiliation_strings":["Microsoft Research, Redmond, United States of America"],"raw_orcid":"https://orcid.org/0009-0006-2694-4685","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, United States of America","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101304603","display_name":"Liangyu Zhao","orcid":"https://orcid.org/0009-0007-5794-0326"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangyu Zhao","raw_affiliation_strings":["University of Washington, Seattle, USA"],"raw_orcid":"https://orcid.org/0009-0007-5794-0326","affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101890152","display_name":"Vincent Liu","orcid":"https://orcid.org/0000-0001-7683-208X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Liu","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-7683-208X","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, United States of America","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103345094","display_name":"Miguel Castro","orcid":"https://orcid.org/0000-0001-6197-0818"},"institutions":[{"id":"https://openalex.org/I4210161460","display_name":"OpenAI (United States)","ror":"https://ror.org/05wx9n238","country_code":"US","type":"company","lineage":["https://openalex.org/I4210161460"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miguel Castro","raw_affiliation_strings":["OpenAI, San Francisco, USA"],"raw_orcid":"https://orcid.org/0000-0001-6197-0818","affiliations":[{"raw_affiliation_string":"OpenAI, San Francisco, USA","institution_ids":["https://openalex.org/I4210161460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023881736","display_name":"Srikanth Kandula","orcid":"https://orcid.org/0000-0001-9494-6435"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srikanth Kandula","raw_affiliation_strings":["Microsoft, Redmond, United States of America"],"raw_orcid":"https://orcid.org/0000-0001-9494-6435","affiliations":[{"raw_affiliation_string":"Microsoft, Redmond, United States of America","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018095091","display_name":"Luke Marshall","orcid":"https://orcid.org/0000-0003-0633-4004"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luke Marshall","raw_affiliation_strings":["Microsoft Research, Redmond, USA"],"raw_orcid":"https://orcid.org/0000-0003-0633-4004","affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9995999932289124,"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":0.9995999932289124,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9970999956130981,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6820755004882812},{"id":"https://openalex.org/keywords/commodity","display_name":"Commodity","score":0.5828565359115601},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5260103940963745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32951414585113525},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.22857427597045898},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06421777606010437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820755004882812},{"id":"https://openalex.org/C2779439359","wikidata":"https://www.wikidata.org/wiki/Q317088","display_name":"Commodity","level":2,"score":0.5828565359115601},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5260103940963745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32951414585113525},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.22857427597045898},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06421777606010437},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3651890.3672249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3651890.3672249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2024 Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G7327530771","display_name":null,"funder_award_id":"CNS-2107147","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320309370","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10"},{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1914921536","https://openalex.org/W1969483458","https://openalex.org/W1983799289","https://openalex.org/W2031407623","https://openalex.org/W2102090846","https://openalex.org/W2160015360","https://openalex.org/W2166102903","https://openalex.org/W2170644767","https://openalex.org/W3072623287","https://openalex.org/W3117684406","https://openalex.org/W3129488589","https://openalex.org/W3203600045","https://openalex.org/W4221157717","https://openalex.org/W4236202168","https://openalex.org/W4281790033","https://openalex.org/W4285071004","https://openalex.org/W4288093768","https://openalex.org/W4308966099","https://openalex.org/W4318541593","https://openalex.org/W4366084930","https://openalex.org/W4395073435","https://openalex.org/W6769475105"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Cloud":[0],"operators":[1],"utilize":[2],"collective":[3,44],"communication":[4],"optimizers":[5,21],"to":[6,23,43,47,79],"enhance":[7],"the":[8,11],"efficiency":[9],"of":[10,70,99],"single-tenant,":[12],"centrally":[13],"managed":[14],"training":[15],"clusters":[16],"they":[17],"manage.":[18],"However,":[19],"current":[20],"struggle":[22],"scale":[24],"for":[25,34],"such":[26],"use":[27],"cases":[28],"and":[29,93],"often":[30],"compromise":[31],"solution":[32],"quality":[33],"scalability.":[35],"Our":[36],"solution,":[37],"TE-CCL,":[38],"adopts":[39],"a":[40,48,67],"traffic-engineering-based":[41],"approach":[42],"communication.":[45],"Compared":[46],"state-of-the-art":[49],"optimizer,":[50],"TACCL,":[51],"TE-CCL":[52,88],"produced":[53],"schedules":[54],"with":[55],"2\u00d7":[56],"better":[57],"performance":[58],"on":[59],"topologies":[60,81],"TACCL":[61,90],"supports":[62],"(and":[63],"its":[64],"solver":[65],"took":[66],"similar":[68],"amount":[69],"time":[71],"as":[72],"TACCL's":[73],"heuristic-based":[74],"approach).":[75],"TECCL":[76],"additionally":[77],"scales":[78],"larger":[80],"than":[82],"TACCL.":[83],"On":[84],"our":[85],"GPU":[86],"testbed,":[87],"outperformed":[89],"by":[91,95],"2.14\u00d7":[92],"RCCL":[94],"3.18\u00d7":[96],"in":[97],"terms":[98],"algorithm":[100],"bandwidth.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}