{"id":"https://openalex.org/W3216007342","doi":"https://doi.org/10.1145/3493649.3493654","title":"Designing a Kubernetes Operator for Machine Learning Applications","display_name":"Designing a Kubernetes Operator for Machine Learning Applications","publication_year":2021,"publication_date":"2021-11-25","ids":{"openalex":"https://openalex.org/W3216007342","doi":"https://doi.org/10.1145/3493649.3493654","mag":"3216007342"},"language":"en","primary_location":{"id":"doi:10.1145/3493649.3493654","doi":"https://doi.org/10.1145/3493649.3493654","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493649.3493654","pdf_url":null,"source":{"id":"https://openalex.org/S7407119824","display_name":"International Workshop on Container Technologies and Container Clouds (WoC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh International Workshop on Container Technologies and Container Clouds","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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":null,"display_name":"Ali Kanso","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Kanso","raw_affiliation_strings":["Machine Teaching Group, Microsoft, Bellevue, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Teaching Group, Microsoft, Bellevue, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071051989","display_name":"Edi Palencia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edi Palencia","raw_affiliation_strings":["Machine Teaching Group, Microsoft, Bellevue, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Teaching Group, Microsoft, Bellevue, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016338652","display_name":"Kinshuman Patra","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kinshuman Patra","raw_affiliation_strings":["Machine Teaching Group, Microsoft, Bellevue, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Teaching Group, Microsoft, Bellevue, Washington, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaxin Shan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxin Shan","raw_affiliation_strings":["Infrastructure Lab, Bytedance, Bellevue, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infrastructure Lab, Bytedance, Bellevue, Washington, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080011633","display_name":"Mengyuan Chao","orcid":"https://orcid.org/0000-0002-1516-0280","observed_orcids":["https://orcid.org/0000-0002-1516-0280"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengyuan Chao","raw_affiliation_strings":["Infrastructure Lab, Bytedance, Bellevue, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infrastructure Lab, Bytedance, Bellevue, Washington, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101650918","display_name":"Wei Zhi Xu","orcid":"https://orcid.org/0000-0001-6632-3062","observed_orcids":["https://orcid.org/0000-0001-6632-3062"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Wei","raw_affiliation_strings":["Infrastructure Lab, Bytedance, Bellevue, Washington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Infrastructure Lab, Bytedance, Bellevue, Washington, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044414487","display_name":"Tengwei Cai","orcid":"https://orcid.org/0009-0003-4757-057X","observed_orcids":["https://orcid.org/0009-0003-4757-057X"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tengwei Cai","raw_affiliation_strings":["Computing Intelligence Department, Ant Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Intelligence Department, Ant Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447188","display_name":"Kang Chen","orcid":"https://orcid.org/0000-0002-2376-2898","observed_orcids":["https://orcid.org/0000-0002-2376-2898"]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Chen","raw_affiliation_strings":["Computing Intelligence Department, Ant Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Intelligence Department, Ant Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4405270328"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101178223","display_name":"Shuai Qiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405270328","display_name":"Ant Group (China)","ror":"https://ror.org/00g5w7n47","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405270328"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Qiao","raw_affiliation_strings":["Computing Intelligence Department, Ant Group, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computing Intelligence Department, Ant Group, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I4405270328"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0048,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.73943572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9520999789237976,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.01590000092983246,"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/T12127","display_name":"Software System Performance and Reliability","score":0.0142000000923872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kubernetes-operator","display_name":"Kubernetes operator","score":0.9599999785423279},{"id":"https://openalex.org/keywords/machine-learning-workloads","display_name":"machine learning workloads","score":0.8289999961853027},{"id":"https://openalex.org/keywords/hyperparameter-optimization","display_name":"hyperparameter optimization","score":0.8339999914169312},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.7009999752044678},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"distributed computing","score":0.675000011920929},{"id":"https://openalex.org/keywords/cluster-management","display_name":"cluster management","score":0.5609999895095825},{"id":"https://openalex.org/keywords/container-orchestration","display_name":"container orchestration","score":0.6589999794960022},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.40799999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8725377321243286},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7324780225753784},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6600621938705444},{"id":"https://openalex.org/C169468491","wikidata":"https://www.wikidata.org/wiki/Q146923","display_name":"Middleware (distributed applications)","level":2,"score":0.6240178942680359},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.6156968474388123},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5528438687324524},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5169838666915894},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4618273079395294},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.44174522161483765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.423300176858902},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4223073422908783},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2569834887981415},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3493649.3493654","doi":"https://doi.org/10.1145/3493649.3493654","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493649.3493654","pdf_url":null,"source":{"id":"https://openalex.org/S7407119824","display_name":"International Workshop on Container Technologies and Container Clouds (WoC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventh International Workshop on Container Technologies and Container Clouds","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2936973201","https://openalex.org/W2969644839","https://openalex.org/W3081233525","https://openalex.org/W3127529544"],"related_works":["https://openalex.org/W3136844352","https://openalex.org/W6959719597","https://openalex.org/W7219476982","https://openalex.org/W7170560015","https://openalex.org/W7152375627","https://openalex.org/W3081233525","https://openalex.org/W4386105260","https://openalex.org/W6968283556","https://openalex.org/W7172497172","https://openalex.org/W7206841285"],"abstract_inverted_index":{"Machine":[0],"Learning":[1],"workloads":[2],"such":[3],"as":[4],"deep":[5],"learning":[6,21,37,51],"and":[7,63,77,91,106,111,130],"hyperparameter":[8],"tuning":[9],"are":[10],"compute-intensive":[11],"by":[12],"nature.":[13],"Parallel":[14],"execution":[15,39],"is":[16,26,58,88],"key":[17],"to":[18,33,75,113],"reducing":[19],"the":[20,67,73,133],"time.":[22],"The":[23],"Ray":[24,48,55,115],"Framework":[25],"a":[27,41,47,54,84,89],"distributed":[28],"middleware":[29],"that":[30,57],"provides":[31],"primitives":[32],"seamlessly":[34],"parallelize":[35],"machine":[36,50],"code":[38],"across":[40],"cluster":[42,56,85,116],"of":[43,108,135],"compute":[44],"node.":[45],"Launching":[46],"managed":[49],"application":[52],"requires":[53],"diligently":[59],"configured,":[60],"well":[61],"connected":[62],"easily":[64],"scalable.":[65],"Kubernetes,":[66,87],"container":[68],"management":[69],"middleware,":[70],"satisfies":[71],"all":[72],"requirements":[74],"create":[76,114],"scale":[78],"ray":[79],"clusters.":[80],"However,":[81],"setting":[82],"up":[83],"within":[86],"tedious":[90],"error":[92],"prone":[93],"task":[94],"when":[95],"done":[96],"manually.":[97],"In":[98],"this":[99],"paper":[100],"we":[101,131],"present":[102,123],"KubeRay,":[103],"an":[104],"Operator":[105],"suite":[107],"tools":[109],"designed,":[110],"built":[112],"in":[117],"Kubernetes":[118],"with":[119],"minimum":[120],"effort.":[121],"We":[122],"our":[124,127,136],"architectural":[125],"choices,":[126],"open-source":[128],"implementation,":[129],"analyze":[132],"performance":[134],"solution.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-12-06T00:00:00"}
