{"id":"https://openalex.org/W4386396242","doi":"https://doi.org/10.1145/3603269.3604869","title":"Janus: A Unified Distributed Training Framework for Sparse Mixture-of-Experts Models","display_name":"Janus: A Unified Distributed Training Framework for Sparse Mixture-of-Experts Models","publication_year":2023,"publication_date":"2023-09-01","ids":{"openalex":"https://openalex.org/W4386396242","doi":"https://doi.org/10.1145/3603269.3604869"},"language":"en","primary_location":{"id":"doi:10.1145/3603269.3604869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603269.3604869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603269.3604869","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 ACM SIGCOMM 2023 Conference","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/10.1145/3603269.3604869","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015855316","display_name":"Juncai Liu","orcid":"https://orcid.org/0000-0001-5783-731X"},"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":"Juncai Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5783-731X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075088248","display_name":"Jessie Hui Wang","orcid":"https://orcid.org/0000-0002-7825-4137"},"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":"Jessie Hui Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China","Zhongguancun Laboratory, Beijing, China","Tsinghua University, Beijing, China Zhongguancun Laboratory, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7825-4137","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Zhongguancun Laboratory, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China Zhongguancun Laboratory, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079353641","display_name":"Yimin Jiang","orcid":"https://orcid.org/0009-0001-0049-873X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yimin Jiang","raw_affiliation_strings":["bytedance, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-0049-873X","affiliations":[{"raw_affiliation_string":"bytedance, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015855316"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":9.4621,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.98170449,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"486","last_page":"498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.989300012588501,"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/computer-science","display_name":"Computer science","score":0.7669483423233032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.560517430305481},{"id":"https://openalex.org/keywords/janus","display_name":"Janus","score":0.5548906922340393},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5486942529678345},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5232452750205994},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.511223554611206},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5023186206817627},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4660319685935974},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42274874448776245},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3475089967250824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7669483423233032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.560517430305481},{"id":"https://openalex.org/C2779290492","wikidata":"https://www.wikidata.org/wiki/Q6155940","display_name":"Janus","level":2,"score":0.5548906922340393},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5486942529678345},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5232452750205994},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.511223554611206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5023186206817627},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4660319685935974},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42274874448776245},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3475089967250824},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3603269.3604869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603269.3604869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603269.3604869","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 ACM SIGCOMM 2023 Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3603269.3604869","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3603269.3604869","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3603269.3604869","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 ACM SIGCOMM 2023 Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G7077520377","display_name":null,"funder_award_id":"62072269","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/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386396242.pdf","grobid_xml":"https://content.openalex.org/works/W4386396242.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2970971581","https://openalex.org/W3034709327","https://openalex.org/W3080189354","https://openalex.org/W3096403968","https://openalex.org/W3119866685","https://openalex.org/W3129831491","https://openalex.org/W3138516171","https://openalex.org/W3147874613","https://openalex.org/W3155127799","https://openalex.org/W3204998121","https://openalex.org/W4200634402","https://openalex.org/W4220967350","https://openalex.org/W4221158240","https://openalex.org/W4226278401","https://openalex.org/W4226515448","https://openalex.org/W4287391717","https://openalex.org/W6739901393","https://openalex.org/W6778883912","https://openalex.org/W6810475161","https://openalex.org/W6815833287"],"related_works":["https://openalex.org/W3127131576","https://openalex.org/W4401226765","https://openalex.org/W993170344","https://openalex.org/W3045240077","https://openalex.org/W2944172132","https://openalex.org/W3101598353","https://openalex.org/W4297129665","https://openalex.org/W4220908867","https://openalex.org/W2951407979","https://openalex.org/W2278415782"],"abstract_inverted_index":{"Scaling":[0],"models":[1,30],"to":[2,5,24,38],"large":[3],"sizes":[4],"improve":[6],"performance":[7],"has":[8],"led":[9],"a":[10,21],"trend":[11],"in":[12,31],"deep":[13],"learning,":[14],"and":[15],"sparsely":[16],"activated":[17],"Mixture-of-Expert":[18],"(MoE)":[19],"is":[20,34],"promising":[22],"architecture":[23],"scale":[25],"models.":[26],"However,":[27],"training":[28],"MoE":[29],"existing":[32],"systems":[33],"expensive,":[35],"mainly":[36],"due":[37],"the":[39],"All-to-All":[40],"communication":[41],"between":[42],"layers.":[43]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}