{"id":"https://openalex.org/W4414170713","doi":"https://doi.org/10.1109/iwqos65803.2025.11143277","title":"eACGM: Non-Instrumented Performance Tracing and Anomaly Detection Towards Machine Learning Systems","display_name":"eACGM: Non-Instrumented Performance Tracing and Anomaly Detection Towards Machine Learning Systems","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4414170713","doi":"https://doi.org/10.1109/iwqos65803.2025.11143277"},"language":"en","primary_location":{"id":"doi:10.1109/iwqos65803.2025.11143277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100958778","display_name":"Ruilin Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruilin Xu","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zongxuan Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongxuan Xie","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023707916","display_name":"Pengfei Chen","orcid":"https://orcid.org/0000-0001-8306-0081"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou,China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998000264167786,"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":0.9987000226974487,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6363999843597412},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6187000274658203},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6000999808311462},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5825999975204468},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.5558000206947327},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47130000591278076},{"id":"https://openalex.org/keywords/instrumentation","display_name":"Instrumentation (computer programming)","score":0.4478999972343445},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3833000063896179},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.3321000039577484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361999750137329},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6187000274658203},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6000999808311462},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5825999975204468},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5231000185012817},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C118530786","wikidata":"https://www.wikidata.org/wiki/Q1134732","display_name":"Instrumentation (computer programming)","level":2,"score":0.4478999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44279998540878296},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.41110000014305115},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3799000084400177},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C200749887","wikidata":"https://www.wikidata.org/wiki/Q1165574","display_name":"System monitoring","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwqos65803.2025.11143277","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwqos65803.2025.11143277","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM 33rd International Symposium on Quality of Service (IWQoS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2477268016","display_name":null,"funder_award_id":"2024YFB4505904","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2087347434","https://openalex.org/W2127218421","https://openalex.org/W2171867449","https://openalex.org/W2295598076","https://openalex.org/W2296719434","https://openalex.org/W2525528777","https://openalex.org/W2945976633","https://openalex.org/W4205556583","https://openalex.org/W4285247965","https://openalex.org/W4300672471","https://openalex.org/W4385993938","https://openalex.org/W4386378095","https://openalex.org/W4386378201","https://openalex.org/W4394586121","https://openalex.org/W4400762160","https://openalex.org/W4402629736"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"eACGM,":[2,126],"a":[3,62,129],"full-stack":[4],"AI/ML":[5,173],"system":[6,98],"monitoring":[7,151],"framework":[8],"based":[9],"on":[10],"eBPF.":[11],"eACGM":[12,79],"collects":[13],"realtime":[14],"performance":[15,71,137,148,166],"data":[16],"from":[17,31],"key":[18,32],"hardware":[19,89],"components,":[20],"including":[21],"the":[22,68],"GPU":[23,56],"and":[24,39,76,91,100,107,114,131,142,149,156,168],"network":[25],"communication":[26,92],"layer,":[27],"as":[28,30,36,86],"well":[29],"software":[33],"stacks":[34],"such":[35,85],"CUDA,":[37],"Python,":[38],"PyTorch,":[40],"all":[41],"without":[42],"requiring":[43],"any":[44],"code":[45],"instrumentation":[46],"or":[47],"modifications.":[48],"Additionally,":[49],"it":[50],"leverages":[51],"libnvml":[52],"to":[53,67],"gather":[54],"process-level":[55],"resource":[57],"usage":[58],"information.":[59],"By":[60],"applying":[61],"Gaussian":[63],"Mixture":[64],"Model":[65],"(GMM)":[66],"collected":[69],"multidimensional":[70],"metrics":[72],"for":[73,165],"statistical":[74],"modeling":[75],"clustering":[77],"analysis,":[78],"effectively":[80],"identifies":[81],"complex":[82],"failure":[83],"modes,":[84],"latency":[87],"anomalies,":[88],"failures,":[90],"inefficiencies,":[93],"enabling":[94],"rapid":[95],"diagnosis":[96,170],"of":[97],"bottlenecks":[99],"abnormal":[101],"behaviors.":[102],"To":[103],"evaluate":[104],"eACGM's":[105],"effectiveness":[106],"practicality,":[108],"we":[109],"conducted":[110],"extensive":[111],"empirical":[112],"studies":[113],"case":[115],"analyses":[116],"in":[117,158,171],"multinode":[118],"distributed":[119],"training":[120,141],"scenarios.":[121],"The":[122],"results":[123],"demonstrate":[124],"that":[125],"while":[127],"maintaining":[128],"non-intrusive":[130],"low-overhead":[132],"profile,":[133],"successfully":[134],"captures":[135],"critical":[136],"anomalies":[138],"during":[139],"model":[140],"inference.":[143],"Its":[144],"stable":[145],"anomaly":[146],"detection":[147],"comprehensive":[150],"capabilities":[152],"validate":[153],"its":[154],"applicability":[155],"scalability":[157],"real-world":[159],"production":[160],"environments,":[161],"providing":[162],"strong":[163],"support":[164],"optimization":[167],"fault":[169],"large-scale":[172],"systems.":[174]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}