{"id":"https://openalex.org/W4416199230","doi":"https://doi.org/10.1145/3712285.3759794","title":"Effective Node-Level Anomaly Detection in HPC Systems via Coarse-Grained Clustering and Fine-Grained Model Sharing","display_name":"Effective Node-Level Anomaly Detection in HPC Systems via Coarse-Grained Clustering and Fine-Grained Model Sharing","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416199230","doi":"https://doi.org/10.1145/3712285.3759794"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712285.3759794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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":"https://openalex.org/A5103087454","display_name":"Sibo Xia","orcid":"https://orcid.org/0009-0008-2853-9549"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Sibo Xia","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0008-2853-9549","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027731066","display_name":"Yongqian Sun","orcid":"https://orcid.org/0000-0003-0266-7899"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqian Sun","raw_affiliation_strings":["Nankai University, Tianjin, China and Tianjin Key Laboratory of Software Experience and Human Computer Interaction, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0266-7899","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China and Tianjin Key Laboratory of Software Experience and Human Computer Interaction, Tianjin, China","institution_ids":["https://openalex.org/I205237279","https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120496908","display_name":"Xijie Pan","orcid":"https://orcid.org/0009-0000-7357-5313"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xijie Pan","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0000-7357-5313","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036886890","display_name":"Yuan Yuan","orcid":"https://orcid.org/0009-0004-5072-6093"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Yuan","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0004-5072-6093","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072210083","display_name":"Shenglin Zhang","orcid":"https://orcid.org/0000-0003-0330-0028"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenglin Zhang","raw_affiliation_strings":["Nankai University, Tianjin, China and Haihe Laboratory of Information Technology Application Innovation, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-0330-0028","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China and Haihe Laboratory of Information Technology Application Innovation, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046722348","display_name":"Shifen Hu","orcid":"https://orcid.org/0009-0009-1166-2126"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyu Hu","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0009-1166-2126","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114888805","display_name":"Tao Lei","orcid":"https://orcid.org/0009-0007-1282-3089"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Tao","raw_affiliation_strings":["Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0007-1282-3089","affiliations":[{"raw_affiliation_string":"Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063717769","display_name":"Yuqi Li","orcid":"https://orcid.org/0009-0003-0576-2127"},"institutions":[{"id":"https://openalex.org/I4210165734","display_name":"National Supercomputing Center of Tianjin","ror":"https://ror.org/05tngxm14","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210165734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Li","raw_affiliation_strings":["National University of Defense Technology, Changsha, China and National Supercomputer Center in Tianjin, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0003-0576-2127","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China and National Supercomputer Center in Tianjin, Tianjin, China","institution_ids":["https://openalex.org/I4210165734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006037378","display_name":"Jinghua Feng","orcid":"https://orcid.org/0009-0006-9657-3584"},"institutions":[{"id":"https://openalex.org/I4210165734","display_name":"National Supercomputing Center of Tianjin","ror":"https://ror.org/05tngxm14","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210165734"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Feng","raw_affiliation_strings":["National Supercomputer Center in Tianjin, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0006-9657-3584","affiliations":[{"raw_affiliation_string":"National Supercomputer Center in Tianjin, Tianjin, China","institution_ids":["https://openalex.org/I4210165734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5103087454"],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":1.3517,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.87168412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1180","last_page":"1194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.4650000035762787,"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":0.4650000035762787,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.1737000048160553,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.08789999783039093,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7430999875068665},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6782000064849854},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5863999724388123},{"id":"https://openalex.org/keywords/codebase","display_name":"Codebase","score":0.5386999845504761},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5160999894142151},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4447000026702881}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753000259399414},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7430999875068665},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6782000064849854},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5479999780654907},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.5386999845504761},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45080000162124634},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26589998602867126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759794","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712285.3759794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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":43,"referenced_works":["https://openalex.org/W2891041086","https://openalex.org/W3011304563","https://openalex.org/W3012919764","https://openalex.org/W3095741830","https://openalex.org/W3097491564","https://openalex.org/W3118600296","https://openalex.org/W3121301634","https://openalex.org/W3152601077","https://openalex.org/W3165758957","https://openalex.org/W3170172454","https://openalex.org/W3176300058","https://openalex.org/W3177318507","https://openalex.org/W3194186453","https://openalex.org/W4213017459","https://openalex.org/W4220967350","https://openalex.org/W4224310748","https://openalex.org/W4226375347","https://openalex.org/W4256138007","https://openalex.org/W4283318673","https://openalex.org/W4291910533","https://openalex.org/W4312204532","https://openalex.org/W4312691182","https://openalex.org/W4312891154","https://openalex.org/W4312901686","https://openalex.org/W4313433600","https://openalex.org/W4379382413","https://openalex.org/W4380520367","https://openalex.org/W4382202513","https://openalex.org/W4382239503","https://openalex.org/W4382322788","https://openalex.org/W4385562572","https://openalex.org/W4386867891","https://openalex.org/W4388094074","https://openalex.org/W4388212302","https://openalex.org/W4388581099","https://openalex.org/W4388697929","https://openalex.org/W4392613491","https://openalex.org/W4394923534","https://openalex.org/W4396820856","https://openalex.org/W4396913945","https://openalex.org/W4401211627","https://openalex.org/W4401856672","https://openalex.org/W4401857088"],"related_works":[],"abstract_inverted_index":{"High-performance":[0],"computing":[1],"(HPC)":[2],"systems":[3],"are":[4],"crucial":[5],"for":[6,34,138],"scientific":[7],"advancement":[8],"and":[9,49,67,115,126,132],"engineering":[10],"breakthroughs.":[11],"Unexpected":[12],"performance":[13],"degradation":[14],"or":[15],"system":[16],"failures":[17],"can":[18],"severely":[19],"impact":[20],"these":[21],"endeavors.":[22],"This":[23,90],"paper":[24],"introduces":[25],"NodeSentry,":[26],"a":[27,43,92,128],"novel":[28,129],"unsupervised":[29],"anomaly":[30,133],"detection":[31],"framework":[32],"tailored":[33],"compute":[35],"nodes":[36],"of":[37,46,71,109],"large-scale":[38],"HPC":[39,73,79,139],"systems.":[40,140],"NodeSentry":[41],"leverages":[42],"combined":[44],"approach":[45],"coarse-grained":[47],"clustering":[48,130],"fine-grained":[50],"model":[51],"sharing":[52],"to":[53,112,117],"effectively":[54],"address":[55],"the":[56,60,118],"challenges":[57],"posed":[58],"by":[59,106],"massive":[61],"node":[62],"scales,":[63],"frequent":[64],"job":[65],"transitions,":[66],"complex":[68],"patterns":[69],"characteristic":[70],"modern":[72],"deployments.":[74],"Evaluation":[75],"on":[76],"two":[77],"real-world":[78],"datasets":[80],"demonstrates":[81],"NodeSentry\u2019s":[82,124],"superior":[83],"performance,":[84],"achieving":[85],"an":[86,107],"F1-score":[87],"exceeding":[88],"0.876.":[89],"represents":[91],"0.560":[93],"average":[94,108],"improvement":[95],"over":[96],"existing":[97],"best":[98],"baseline":[99],"methods,":[100],"while":[101],"simultaneously":[102],"reducing":[103],"training":[104],"overhead":[105],"45.69%.":[110],"Furthermore,":[111],"promote":[113],"reproducibility":[114],"contribute":[116],"broader":[119],"research":[120],"community,":[121],"we":[122],"open-source":[123],"codebase":[125],"introduce":[127],"adjustment":[131],"labeling":[134],"tool":[135],"specifically":[136],"designed":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-28T07:36:58.565527","created_date":"2025-11-12T00:00:00"}