{"id":"https://openalex.org/W7117785012","doi":"https://doi.org/10.1145/3737611.3776945","title":"High-Reliability Network-Distributed MoE-LLM System","display_name":"High-Reliability Network-Distributed MoE-LLM System","publication_year":2025,"publication_date":"2025-12-31","ids":{"openalex":"https://openalex.org/W7117785012","doi":"https://doi.org/10.1145/3737611.3776945"},"language":null,"primary_location":{"id":"doi:10.1145/3737611.3776945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3737611.3776945","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 27th International Conference on Distributed Computing and Networking","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3737611.3776945","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023279673","display_name":"Haruki Yonekura","orcid":"https://orcid.org/0000-0001-8184-3883"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruki Yonekura","raw_affiliation_strings":["The University of Osaka, Suita, Japan and RIKEN Center for Computational Science, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8184-3883","affiliations":[{"raw_affiliation_string":"The University of Osaka, Suita, Japan and RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009031118","display_name":"H. Yamaguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirozumi Yamaguchi","raw_affiliation_strings":["The University of Osaka, Suita, Japan and RIKEN Center for Computational Science, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2273-4876","affiliations":[{"raw_affiliation_string":"The University of Osaka, Suita, Japan and RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.08749999850988388,"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/T12127","display_name":"Software System Performance and Reliability","score":0.08749999850988388,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.07859999686479568,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.07039999961853027,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6955999732017517},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5996000170707703},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4408000111579895},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4341000020503998},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.37630000710487366},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.33899998664855957}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6955999732017517},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5645999908447266},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.45739999413490295},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4408000111579895},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.3986999988555908},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3917999863624573},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.37439998984336853},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C107094494","wikidata":"https://www.wikidata.org/wiki/Q428453","display_name":"Fault tree analysis","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C165136773","wikidata":"https://www.wikidata.org/wiki/Q1363179","display_name":"Single point of failure","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C31352089","wikidata":"https://www.wikidata.org/wiki/Q3750474","display_name":"Systems design","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2734000086784363}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3737611.3776945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3737611.3776945","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 27th International Conference on Distributed Computing and Networking","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3737611.3776945","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3737611.3776945","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 27th International Conference on Distributed Computing and Networking","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6268871426582336,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G6062912269","display_name":null,"funder_award_id":"JPMJAX25MJ","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G6306087798","display_name":null,"funder_award_id":"23H03384","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"For":[0],"the":[1,52,79,82,119],"practical":[2],"deployment":[3],"of":[4,54,81],"distributed":[5,29,115],"Mixture-of-Experts":[6],"large":[7],"language":[8],"models(MoE-LLM),":[9],"ensuring":[10],"resilience":[11],"is":[12],"as":[13,15,57,59],"critical":[14],"achieving":[16],"computational":[17],"efficiency.":[18],"This":[19],"research":[20],"tackles":[21],"this":[22,101],"pressing":[23],"challenge":[24],"by":[25],"introducing":[26],"a":[27,74,85],"resilient":[28],"LLM":[30,116],"architecture":[31],"that":[32,48,62],"dynamically":[33],"maintains":[34],"system":[35,91],"reliability":[36,53],"in":[37],"large-scale":[38],"networked":[39],"environments.":[40],"The":[41],"proposed":[42],"framework":[43,77],"develops":[44],"cooperative":[45],"routing":[46],"mechanisms":[47,61],"adaptively":[49],"account":[50],"for":[51,109,121],"individual":[55],"Experts,":[56],"well":[58],"resistance":[60],"mitigate":[63],"cascade":[64],"failures":[65],"and":[66,95,113,124],"suppress":[67],"malicious":[68],"Expert":[69],"behaviors.":[70],"Furthermore,":[71],"it":[72],"establishes":[73],"quantitative":[75],"evaluation":[76],"through":[78],"introduction":[80],"Resilience":[83],"Score,":[84],"comprehensive":[86],"metric":[87],"designed":[88],"to":[89,104],"assess":[90],"robustness":[92],"under":[93],"fault":[94],"attack":[96],"conditions.":[97],"Through":[98],"these":[99],"contributions,":[100],"study":[102],"aims":[103],"provide":[105],"foundational":[106],"design":[107],"principles":[108],"constructing":[110],"trustworthy,":[111],"fault-tolerant,":[112],"high-performance":[114],"systems,":[117],"paving":[118],"way":[120],"their":[122],"safe":[123],"reliable":[125],"integration":[126],"into":[127],"future":[128],"cyber-physical":[129],"infrastructures.":[130]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-31T00:00:00"}
