{"id":"https://openalex.org/W4220967350","doi":"https://doi.org/10.1145/3503221.3508418","title":"FasterMoE","display_name":"FasterMoE","publication_year":2022,"publication_date":"2022-03-28","ids":{"openalex":"https://openalex.org/W4220967350","doi":"https://doi.org/10.1145/3503221.3508418"},"language":"en","primary_location":{"id":"doi:10.1145/3503221.3508418","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503221.3508418","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503221.3508418","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/10.1145/3503221.3508418","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066744881","display_name":"Jiaao He","orcid":"https://orcid.org/0000-0001-8578-5158"},"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":"Jiaao He","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071200777","display_name":"Jidong Zhai","orcid":"https://orcid.org/0000-0002-7656-6428"},"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":"Jidong Zhai","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103049201","display_name":"Tiago Antunes","orcid":"https://orcid.org/0009-0001-0793-8515"},"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":"Tiago Antunes","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735476","display_name":"Haojie Wang","orcid":"https://orcid.org/0000-0003-4605-148X"},"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":"Haojie Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114124897","display_name":"Fuwen Luo","orcid":null},"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":"Fuwen Luo","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051741117","display_name":"Shangfeng Shi","orcid":null},"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":"Shangfeng Shi","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693735","display_name":"Qin Li","orcid":"https://orcid.org/0000-0001-5172-324X"},"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":"Qin Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5066744881"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":14.6985,"has_fulltext":true,"cited_by_count":69,"citation_normalized_percentile":{"value":0.99587296,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9962999820709229,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9962999820709229,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9948999881744385,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9897000193595886,"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/computer-science","display_name":"Computer science","score":0.8187816143035889},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6060928106307983},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5835260152816772},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5659222602844238},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5105217695236206},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.49448180198669434},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4772876799106598},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17803040146827698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187816143035889},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6060928106307983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835260152816772},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5659222602844238},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5105217695236206},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.49448180198669434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4772876799106598},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17803040146827698},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503221.3508418","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503221.3508418","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503221.3508418","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503221.3508418","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503221.3508418","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503221.3508418","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7619151073","display_name":null,"funder_award_id":"U20A20226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320317140","display_name":"National Supercomputer Centre in Guangzhou","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220967350.pdf","grobid_xml":"https://content.openalex.org/works/W4220967350.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2060393849","https://openalex.org/W2066334462","https://openalex.org/W2102061396","https://openalex.org/W2105908643","https://openalex.org/W2499905000","https://openalex.org/W2883830791","https://openalex.org/W2933138175","https://openalex.org/W2967558351","https://openalex.org/W2969388332","https://openalex.org/W3011751313","https://openalex.org/W3081168214","https://openalex.org/W3099748883","https://openalex.org/W3101104221","https://openalex.org/W3129831491","https://openalex.org/W3132107458","https://openalex.org/W4301361180"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4375867731","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4380075502"],"abstract_inverted_index":{"The":[0],"current":[1],"trend":[2],"in":[3,51],"deep":[4,74],"learning":[5,75],"is":[6,23],"to":[7,10,41,81],"scale":[8],"models":[9,35],"extremely":[11],"large":[12],"sizes":[13],"with":[14,36],"the":[15,24,32,42,63,82],"objective":[16],"of":[17,34,45,59,84],"increasing":[18],"their":[19],"accuracy.":[20],"Mixture-of-Expert":[21],"(MoE)":[22],"most":[25],"popular":[26],"pre-trained":[27],"model":[28,66],"that":[29],"makes":[30],"feasible":[31],"training":[33,58,86],"parameters":[37],"beyond":[38],"trillion-scale.":[39],"Thanks":[40],"dynamic":[43,89],"activation":[44],"experts,":[46],"i.e.,":[47],"shallow":[48],"layers":[49],"specialized":[50],"certain":[52],"domains,":[53],"it":[54,77],"allows":[55],"for":[56],"sparse":[57],"bigger":[60],"models,":[61,76],"removing":[62],"linearity":[64],"between":[65],"size":[67],"and":[68,96],"computation.":[69],"However,":[70],"different":[71],"from":[72],"traditional":[73],"draws":[78],"huge":[79],"challenges":[80],"efficiency":[83],"these":[85],"systems,":[87],"including":[88],"load":[90],"imbalance,":[91],"inefficient":[92],"synchronous":[93],"execution":[94],"mode,":[95],"congested":[97],"all-to-all":[98],"communication.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2022-04-03T00:00:00"}