{"id":"https://openalex.org/W7124149196","doi":"https://doi.org/10.1109/icpads67057.2025.11322876","title":"An Efficient Online AlltoAll Scheduling Framework for Mixture-of-Experts","display_name":"An Efficient Online AlltoAll Scheduling Framework for Mixture-of-Experts","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124149196","doi":"https://doi.org/10.1109/icpads67057.2025.11322876"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11322876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11322876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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":null,"display_name":"Junkai Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junkai Huang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100642528","display_name":"Yufan Yang","orcid":"https://orcid.org/0000-0001-7460-8164"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiling Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71065008,"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/T13553","display_name":"Age of Information Optimization","score":0.66839998960495,"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/T13553","display_name":"Age of Information Optimization","score":0.66839998960495,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.07419999688863754,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.06729999929666519,"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/scheduling","display_name":"Scheduling (production processes)","score":0.6396999955177307},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48829999566078186},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.31189998984336853},{"id":"https://openalex.org/keywords/job-shop-scheduling","display_name":"Job shop scheduling","score":0.3061000108718872},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2946000099182129}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7132999897003174},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48829999566078186},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42590001225471497},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.3061000108718872},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.27570000290870667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11322876","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11322876","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W4318541593","https://openalex.org/W4402044182"],"related_works":[],"abstract_inverted_index":{"AlltoAll":[0,27,66],"communication":[1],"in":[2],"online":[3,26],"Mixture-of-Experts":[4],"inference":[5],"inherently":[6],"produces":[7],"severe":[8],"incast":[9,33],"that":[10,29],"can":[11],"overwhelm":[12],"transport,":[13],"inflate":[14],"switch":[15],"queues,":[16],"and":[17,34,56],"raise":[18],"tail":[19],"latency.":[20],"We":[21],"present":[22],"a":[23,39],"lightweight,":[24],"deployable":[25],"scheduler":[28],"aims":[30],"to":[31,38,71],"mitigate":[32],"return":[35],"the":[36],"system":[37],"congestion-control-manageable":[40],"regime,":[41],"rather":[42],"than":[43],"pursuing":[44],"global":[45],"optimality.":[46],"Our":[47],"design":[48],"integrates:":[49],"(i)":[50],"expert-load":[51],"prediction;":[52],"(ii)":[53],"max-matching-based":[54],"scheduling;":[55],"(iii)":[57],"congestion-aware":[58],"rescheduling.":[59],"Preliminary":[60],"experiments":[61],"show":[62],"our":[63],"approach":[64],"reduces":[65],"completion":[67],"time":[68],"by":[69],"up":[70],"15.6%.":[72]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-01-15T00:00:00"}