{"id":"https://openalex.org/W7204268483","doi":"https://doi.org/10.1109/iwqos70441.2026.11661181","title":"MAS-CP: Multi-Agent Communication Prediction for Distributed Deep Neural Network Training","display_name":"MAS-CP: Multi-Agent Communication Prediction for Distributed Deep Neural Network Training","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7204268483","doi":"https://doi.org/10.1109/iwqos70441.2026.11661181"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos70441.2026.11661181","doi":"https://doi.org/10.1109/iwqos70441.2026.11661181","is_oa":true,"landing_page_url":"https://doi.org/10.1109/iwqos70441.2026.11661181","pdf_url":null,"source":{"id":"https://openalex.org/S4210234387","display_name":"International Workshop on Quality of Service","issn_l":"1548-615X","issn":["1548-615X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/iwqos70441.2026.11661181","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120211369","display_name":"Zijie Huang","orcid":"https://orcid.org/0000-0002-8911-9889","observed_orcids":["https://orcid.org/0000-0002-8911-9889"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijie Huang","raw_affiliation_strings":["Shanghai Software Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Software Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130229999","display_name":"Zixuan Chen","orcid":"https://orcid.org/0000-0002-0126-0387","observed_orcids":["https://orcid.org/0000-0002-0126-0387"]},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Chen","raw_affiliation_strings":["Cloud Computing Research Institute China Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cloud Computing Research Institute China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064559431","display_name":"Kai Shi","orcid":"https://orcid.org/0000-0002-0077-719X","observed_orcids":["https://orcid.org/0000-0002-0077-719X"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Shi","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5820000171661377,"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":0.5820000171661377,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.12919999659061432,"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/T12127","display_name":"Software System Performance and Reliability","score":0.061400000005960464,"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/multi-agent-systems","display_name":"multi-agent systems","score":0.671999990940094},{"id":"https://openalex.org/keywords/distributed-deep-neural-network-training","display_name":"distributed deep neural network training","score":0.972000002861023},{"id":"https://openalex.org/keywords/closed-loop-verification","display_name":"closed-loop verification","score":0.8640000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539999842643738},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5411999821662903},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.27570000290870667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos70441.2026.11661181","doi":"https://doi.org/10.1109/iwqos70441.2026.11661181","is_oa":true,"landing_page_url":"https://doi.org/10.1109/iwqos70441.2026.11661181","pdf_url":null,"source":{"id":"https://openalex.org/S4210234387","display_name":"International Workshop on Quality of Service","issn_l":"1548-615X","issn":["1548-615X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/iwqos70441.2026.11661181","doi":"https://doi.org/10.1109/iwqos70441.2026.11661181","is_oa":true,"landing_page_url":"https://doi.org/10.1109/iwqos70441.2026.11661181","pdf_url":null,"source":{"id":"https://openalex.org/S4210234387","display_name":"International Workshop on Quality of Service","issn_l":"1548-615X","issn":["1548-615X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/ACM International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4408284970"],"related_works":["https://openalex.org/W7204235619","https://openalex.org/W4386260397","https://openalex.org/W7133188823","https://openalex.org/W4411949123","https://openalex.org/W7166740502","https://openalex.org/W156577818","https://openalex.org/W2807897761","https://openalex.org/W7204241201","https://openalex.org/W3215549520","https://openalex.org/W7130869251"],"abstract_inverted_index":{"Predicting":[0],"all-reduce":[1],"communication":[2],"latency":[3,14],"in":[4],"distributed":[5],"deep":[6],"neural":[7],"network":[8,19],"(DNN)":[9],"training":[10],"is":[11],"challenging":[12],"because":[13],"depends":[15],"on":[16,28],"both":[17],"shared":[18],"state":[20],"and":[21,39,52,58,65],"per-worker":[22],"program":[23],"behavior.":[24],"Existing":[25],"approaches":[26],"rely":[27],"monolithic":[29],"predictors":[30],"with":[31,48,69,89],"fixed":[32],"architectures,":[33],"making":[34],"them":[35],"brittle":[36],"across":[37],"models":[38],"cluster":[40],"sizes.":[41],"We":[42],"propose":[43],"MAS-CP,":[44],"a":[45,90,101],"multi-agent":[46],"framework":[47],"Locator,":[49],"Analyzer,":[50],"Predictor,":[51],"Verifier":[53],"agents":[54],"plus":[55],"an":[56],"orchestrator":[57],"RAG":[59],"memory.":[60],"On":[61],"realworld":[62],"BERT/GPT-2":[63],"traces":[64],"simulated":[66],"multi-worker":[67],"clusters":[68],"worker":[70],"counts":[71],"$W=2,4,8,16$,":[72],"MAS-CP":[73],"reduces":[74],"MAE":[75],"by":[76],"$\\mathbf{3.":[77],"6":[78],"\\%":[79],"-":[80],"6.":[81],"1":[82],"\\%}$":[83],"over":[84],"the":[85],"best":[86],"fixed-configuration":[87],"baselines,":[88],"closed-loop":[91],"verification":[92],"mechanism":[93],"that":[94],"automatically":[95],"triggers":[96],"re-prediction":[97],"when":[98],"errors":[99],"exceed":[100],"dynamic":[102],"threshold.":[103]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-27T00:00:00"}
