{"id":"https://openalex.org/W7169829608","doi":"https://doi.org/10.1145/3820441.3820449","title":"Argus: Scalable and Deterministic Network Fault Localization for AI Training Clusters","display_name":"Argus: Scalable and Deterministic Network Fault Localization for AI Training Clusters","publication_year":2026,"publication_date":"2026-07-21","ids":{"openalex":"https://openalex.org/W7169829608","doi":"https://doi.org/10.1145/3820441.3820449"},"language":null,"primary_location":{"id":"doi:10.1145/3820441.3820449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820441.3820449","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":"Proceedings of the 10th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3820441.3820449","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005753368","display_name":"Yuxiang Wang","orcid":"https://orcid.org/0009-0004-0276-4538"},"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":"Yuxiang Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0276-4538","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100317582","display_name":"Jiao Zhang","orcid":"https://orcid.org/0000-0001-5614-3420"},"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":"Jiao Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5614-3420","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141233215","display_name":"Xianyu Huang","orcid":"https://orcid.org/0009-0004-3167-2413"},"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":"Xianyu Huang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3167-2413","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130548126","display_name":"Yubo Ruan","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":false,"raw_author_name":"Yubo Ruan","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-0306-8430","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141253500","display_name":"Yuxuan Hu","orcid":"https://orcid.org/0009-0006-1801-5704"},"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":"Yuxuan Hu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1801-5704","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141251105","display_name":"Yingjie Duan","orcid":"https://orcid.org/0009-0004-4441-3998"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjie Duan","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-4441-3998","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103055019","display_name":"Shoushou Ren","orcid":"https://orcid.org/0009-0003-8530-5259"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shoushou Ren","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-8530-5259","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104087850","display_name":"Xianjun He","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianjun He","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Chengdu, China"],"raw_orcid":"https://orcid.org/0009-0000-3215-888X","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Chengdu, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067162884","display_name":"Junlong Chen","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":false,"raw_author_name":"Junlong Chen","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-4368-7751","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032538854","display_name":"Y W Li","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":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2068-5315","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/A5087767046","display_name":"Tao Huang","orcid":"https://orcid.org/0000-0002-3545-1122"},"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":"Tao Huang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3545-1122","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":[],"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":"51","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6026999950408936},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.553600013256073},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5263000130653381},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.43650001287460327},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.43619999289512634},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.42879998683929443},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.420199990272522},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.39259999990463257},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.38690000772476196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167999744415283},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6026999950408936},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.553600013256073},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.43619999289512634},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.420199990272522},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34709998965263367},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3820441.3820449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820441.3820449","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":"Proceedings of the 10th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3820441.3820449","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820441.3820449","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":"Proceedings of the 10th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1990249073","https://openalex.org/W2146012756","https://openalex.org/W2809353470","https://openalex.org/W2969388332","https://openalex.org/W3046644368","https://openalex.org/W3046744974","https://openalex.org/W4235732943","https://openalex.org/W4383217692","https://openalex.org/W4386385402","https://openalex.org/W4401175863","https://openalex.org/W4401176521","https://openalex.org/W4401176590","https://openalex.org/W4401176799","https://openalex.org/W4413756585","https://openalex.org/W4413757557"],"related_works":[],"abstract_inverted_index":{"Network":[0],"failures":[1,46,128,171],"in":[2,66],"Artificial":[3],"Intelligence":[4],"(AI)":[5],"training":[6],"clusters":[7],"can":[8],"degrade":[9],"entire":[10],"jobs,":[11],"making":[12],"fast":[13],"and":[14,37,61,117,166],"accurate":[15],"fault":[16,115],"localization":[17,125],"critical.":[18],"Existing":[19],"active":[20],"probing":[21,93],"systems":[22],"suffer":[23],"from":[24],"two":[25],"fundamental":[26],"limitations:":[27],"probabilistic":[28],"path":[29],"coverage":[30,99,152],"that":[31,41,95,146],"cannot":[32],"guarantee":[33],"complete":[34,106],"link":[35,107,151],"observability,":[36],"binary":[38],"anomaly":[39],"detection":[40],"fails":[42],"to":[43,73,101,113,142],"distinguish":[44],"concurrent":[45],"or":[47],"localize":[48],"gray":[49,133,170],"failures.":[50,134],"Equal-Cost":[51],"Multi-Path":[52],"(ECMP)":[53],"routing":[54],"is":[55],"deterministic":[56,98],"given":[57],"the":[58],"same":[59],"5-tuple,":[60],"ECMP":[62],"configurations":[63],"are":[64],"accessible":[65],"operator-controlled":[67],"clusters.":[68],"We":[69,109],"exploit":[70],"this":[71,87],"property":[72],"derive":[74],"exact":[75],"probe":[76],"paths":[77],"through":[78],"offline":[79],"hash":[80],"computation":[81],"without":[82],"network":[83],"measurement.":[84],"Based":[85],"on":[86,137],"approach,":[88],"we":[89],"design":[90],"a":[91,97,118],"hash-aware":[92],"system":[94,148],"constructs":[96],"matrix":[100],"select":[102],"minimal":[103],"probes":[104,156],"guaranteeing":[105],"coverage.":[108],"introduce":[110],"edge":[111],"signatures":[112],"ensure":[114],"distinguishability":[116],"tiered":[119],"diagnosis":[120],"approach":[121],"where":[122,172],"lightweight":[123],"iterative":[124],"handles":[126],"hard":[127],"while":[129],"sparse":[130],"regression":[131],"localizes":[132],"Preliminary":[135],"evaluations":[136],"fat-tree":[138],"topologies":[139],"with":[140,153],"up":[141],"10,240":[143],"hosts":[144],"show":[145],"our":[147],"achieves":[149],"100%":[150],"39\u00d7":[154],"fewer":[155],"than":[157],"R-Pingmesh,":[158],"F1":[159,168],"score":[160],"of":[161],"0.75\u20130.92":[162],"for":[163,169],"multi-link":[164],"failures,":[165],"0.67":[167],"existing":[173],"methods":[174],"fail":[175],"entirely.":[176]},"counts_by_year":[],"updated_date":"2026-07-22T06:00:27.337203","created_date":"2026-07-22T00:00:00"}