{"id":"https://openalex.org/W4392613491","doi":"https://doi.org/10.1109/tpds.2024.3365462","title":"Runtime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning","display_name":"Runtime Performance Anomaly Diagnosis in Production HPC Systems Using Active Learning","publication_year":2024,"publication_date":"2024-02-14","ids":{"openalex":"https://openalex.org/W4392613491","doi":"https://doi.org/10.1109/tpds.2024.3365462"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3365462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3365462","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5067151303","display_name":"Burak Aksar","orcid":"https://orcid.org/0000-0003-3627-7311"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Burak Aksar","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3627-7311","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008438549","display_name":"Efe Sencan","orcid":"https://orcid.org/0009-0008-1097-549X"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Efe Sencan","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0009-0008-1097-549X","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017277772","display_name":"Benjamin Schwaller","orcid":"https://orcid.org/0000-0002-9282-8977"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Schwaller","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":"https://orcid.org/0000-0002-9282-8977","affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030343676","display_name":"Omar Aaziz","orcid":"https://orcid.org/0009-0000-9651-0299"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omar Aaziz","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":"https://orcid.org/0009-0000-9651-0299","affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032598206","display_name":"Vitus J. Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitus J. Leung","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":"https://orcid.org/0009-0008-3950-1626","affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015075548","display_name":"Jim Brandt","orcid":"https://orcid.org/0000-0002-8605-5795"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jim Brandt","raw_affiliation_strings":["Sandia National Laboratories, Albuquerque, NM, USA"],"raw_orcid":"https://orcid.org/0000-0002-8605-5795","affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, NM, USA","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049134079","display_name":"Brian Kulis","orcid":"https://orcid.org/0000-0002-1704-3838"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kulis","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1704-3838","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044975798","display_name":"Manuel Egele","orcid":"https://orcid.org/0000-0001-5038-2682"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuel Egele","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5038-2682","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064676631","display_name":"Ayse K. Coskun","orcid":"https://orcid.org/0000-0002-6554-088X"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayse K. Coskun","raw_affiliation_strings":["Electrical and Computer Engineering Department, Boston University, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6554-088X","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Boston University, Boston, MA, USA","institution_ids":["https://openalex.org/I111088046"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5067151303"],"corresponding_institution_ids":["https://openalex.org/I111088046"],"apc_list":null,"apc_paid":null,"fwci":4.6359,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.95164942,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"35","issue":"4","first_page":"693","last_page":"706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9983999729156494,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9901999831199646,"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":0.9842000007629395,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8602259159088135},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.780348002910614},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.535476803779602},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.5287449359893799},{"id":"https://openalex.org/keywords/telemetry","display_name":"Telemetry","score":0.5114799737930298},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4909549057483673},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4532890319824219},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4022790789604187},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3743930160999298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33522844314575195},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.32607150077819824},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.1426035761833191},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11637136340141296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8602259159088135},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.780348002910614},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.535476803779602},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.5287449359893799},{"id":"https://openalex.org/C183121708","wikidata":"https://www.wikidata.org/wiki/Q209867","display_name":"Telemetry","level":2,"score":0.5114799737930298},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4909549057483673},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4532890319824219},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4022790789604187},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3743930160999298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33522844314575195},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.32607150077819824},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.1426035761833191},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11637136340141296},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3365462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3365462","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W107619411","https://openalex.org/W1481984145","https://openalex.org/W1949554883","https://openalex.org/W1971961903","https://openalex.org/W1986905947","https://openalex.org/W2009223344","https://openalex.org/W2019465613","https://openalex.org/W2038924755","https://openalex.org/W2075714842","https://openalex.org/W2086748522","https://openalex.org/W2100997884","https://openalex.org/W2108334595","https://openalex.org/W2470158437","https://openalex.org/W2613580061","https://openalex.org/W2757481678","https://openalex.org/W2802314367","https://openalex.org/W2802572676","https://openalex.org/W2884697432","https://openalex.org/W2885766119","https://openalex.org/W2888693151","https://openalex.org/W2891041086","https://openalex.org/W2901773810","https://openalex.org/W2903158431","https://openalex.org/W2919913503","https://openalex.org/W2962743733","https://openalex.org/W2965985637","https://openalex.org/W2966734812","https://openalex.org/W2984468687","https://openalex.org/W3026954374","https://openalex.org/W3093253286","https://openalex.org/W3097491564","https://openalex.org/W3122766170","https://openalex.org/W3170172454","https://openalex.org/W3176009043","https://openalex.org/W3198539693","https://openalex.org/W3213434933","https://openalex.org/W4206114897","https://openalex.org/W4206723194","https://openalex.org/W4213009331","https://openalex.org/W4220730878","https://openalex.org/W4224315779","https://openalex.org/W4287882781","https://openalex.org/W4288779706","https://openalex.org/W4312341889","https://openalex.org/W4401830618","https://openalex.org/W6686198202","https://openalex.org/W6745425361","https://openalex.org/W6756615331"],"related_works":["https://openalex.org/W2066858118","https://openalex.org/W1976914335","https://openalex.org/W3011699130","https://openalex.org/W2134017072","https://openalex.org/W2915208987","https://openalex.org/W2152256925","https://openalex.org/W1940452713","https://openalex.org/W2070863773","https://openalex.org/W2018090346","https://openalex.org/W112797016"],"abstract_inverted_index":{"With":[0],"the":[1,41,67,71,83,102,111,114,222,245,249,290],"increasing":[2],"scale":[3],"and":[4,25,53,64,81,110,150,186,192,286],"complexity":[5],"of":[6,44,70,105,120,124,172,206,224],"High-Performance":[7],"Computing":[8],"(HPC)":[9],"systems,":[10,33],"performance":[11,91,156,218],"variations":[12,35,47],"in":[13,22,93,152,227,289],"applications":[14,285],"caused":[15],"by":[16,87],"anomalies":[17,72,182,189,219],"have":[18,138,144],"become":[19,36],"significant":[20,170],"bottlenecks":[21],"system":[23,79,195],"health":[24,80],"operational":[26,55],"efficiency.":[27],"As":[28],"we":[29],"move":[30],"towards":[31],"exascale":[32],"these":[34,59,132],"more":[37],"prominent":[38],"due":[39],"to":[40,49,77,101,126,147,200,238,253],"increased":[42],"sharing":[43],"resources.":[45],"Such":[46],"lead":[48],"lower":[50],"energy":[51],"efficiency":[52],"higher":[54],"costs.":[56],"To":[57],"mitigate":[58],"problems,":[60],"one":[61],"must":[62],"quickly":[63],"accurately":[65],"diagnose":[66,127],"root":[68],"cause":[69],"at":[73,230],"scale.":[74],"One":[75,158],"way":[76],"evaluate":[78],"identify":[82],"underlying":[84],"causes":[85],"is":[86,165,183,198],"manually":[88],"examining":[89],"certain":[90],"metrics":[92],"telemetry":[94,106,116,125,196],"data":[95,107,117,197],"or":[96],"using":[97,232,257],"rule-based":[98],"methods.":[99],"Due":[100],"daily":[103],"size":[104],"reaching":[108],"terabytes":[109],"fact":[112],"that":[113,166,216,244],"numeric":[115,194],"contains":[118,204],"thousands":[119,205],"metrics,":[121],"manual":[122],"analysis":[123],"problems":[128],"becomes":[129],"challenging.":[130],"Given":[131],"limitations,":[133],"Machine":[134],"Learning":[135],"(ML)-based":[136],"approaches":[137],"been":[139,145],"gaining":[140],"popularity":[141],"as":[142],"they":[143,167],"shown":[146],"be":[148],"effective":[149],"practical":[151],"diagnosing":[153],"previously":[154,283],"encountered":[155],"anomalies.":[157],"primary":[159],"challenge":[160],"for":[161,181,266,274],"supervised":[162,255],"ML":[163],"models":[164],"require":[168],"a":[169,211,254,268,276],"amount":[171],"labeled":[173,235,260],"samples":[174,236,261,265,273],"during":[175],"training.":[176],"However,":[177],"obtaining":[178],"many":[179],"labels":[180],"extremely":[184],"difficult":[185],"costly,":[187],"considering":[188],"occur":[190],"infrequently":[191],"real-world":[193],"hard":[199],"label":[201],"since":[202],"it":[203],"metrics.":[207],"This":[208],"paper":[209],"proposes":[210],"novel":[212],"active":[213],"learning-based":[214],"framework":[215,247],"diagnoses":[217],"(i.e.,":[220,262],"identifying":[221],"type":[223],"an":[225],"anomaly)":[226],"HPC":[228],"systems":[229],"runtime":[231],"significantly":[233],"fewer":[234,259,264,272],"compared":[237,252],"state-of-the-art":[239],"ML-based":[240],"approaches.":[241],"We":[242],"show":[243],"proposed":[246],"achieves":[248],"same":[250],"F1-score":[251],"approach":[256],"much":[258],"16x":[263],"achieving":[267,275],"0.78":[269],"F1-score,":[270],"11x":[271],"0.82":[277],"F1-score),":[278],"even":[279],"when":[280],"there":[281],"are":[282],"unseen":[284],"application":[287],"inputs":[288],"test":[291],"dataset.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}