{"id":"https://openalex.org/W4404788205","doi":"https://doi.org/10.1145/3652892.3700767","title":"Cannikin: Optimal Adaptive Distributed DNN Training over Heterogeneous Clusters","display_name":"Cannikin: Optimal Adaptive Distributed DNN Training over Heterogeneous Clusters","publication_year":2024,"publication_date":"2024-11-27","ids":{"openalex":"https://openalex.org/W4404788205","doi":"https://doi.org/10.1145/3652892.3700767"},"language":"en","primary_location":{"id":"doi:10.1145/3652892.3700767","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3652892.3700767","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Middleware Conference","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/A5111127663","display_name":"Chengyi Nie","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chengyi Nie","raw_affiliation_strings":["Stony Brook University, Stony Brook, US"],"raw_orcid":"https://orcid.org/0009-0000-3806-6310","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, US","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091040809","display_name":"Jessica Maghakian","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessica Maghakian","raw_affiliation_strings":["Stony Brook University, Stony Brook, US"],"raw_orcid":"https://orcid.org/0009-0009-6070-7378","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, US","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420216","display_name":"Zhenhua Liu","orcid":"https://orcid.org/0000-0002-8026-4502"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenhua Liu","raw_affiliation_strings":["Stony Brook University, Stony Brook, US"],"raw_orcid":"https://orcid.org/0000-0002-8026-4502","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, US","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111127663"],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":0.6623,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76459995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926000237464905,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926000237464905,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9855999946594238,"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/T12676","display_name":"Machine Learning and ELM","score":0.9837999939918518,"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":0.7719672322273254},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.7343367338180542},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.570493757724762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3454819321632385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719672322273254},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.7343367338180542},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.570493757724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3454819321632385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652892.3700767","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3652892.3700767","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Middleware Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.5,"display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G2275028705","display_name":null,"funder_award_id":"CCF-2046444.","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G414456992","display_name":null,"funder_award_id":"CNS-2214980","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4527358855","display_name":null,"funder_award_id":"CNS-2106027","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G991445300","display_name":null,"funder_award_id":"CNS-2146909","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1602617099","https://openalex.org/W1980032585","https://openalex.org/W2010798306","https://openalex.org/W2057332538","https://openalex.org/W2108598243","https://openalex.org/W2114853176","https://openalex.org/W2193413348","https://openalex.org/W2219888463","https://openalex.org/W2296335794","https://openalex.org/W2525778437","https://openalex.org/W2551437525","https://openalex.org/W2612690371","https://openalex.org/W2734941459","https://openalex.org/W2773689216","https://openalex.org/W2798515322","https://openalex.org/W2896457183","https://openalex.org/W2899915146","https://openalex.org/W2904125685","https://openalex.org/W2949650786","https://openalex.org/W2951707557","https://openalex.org/W2953212265","https://openalex.org/W2953384591","https://openalex.org/W2962725887","https://openalex.org/W2962747323","https://openalex.org/W2963748441","https://openalex.org/W2973727699","https://openalex.org/W2981114289","https://openalex.org/W3004702456","https://openalex.org/W3022298203","https://openalex.org/W3022548332","https://openalex.org/W3106803824","https://openalex.org/W3173623873","https://openalex.org/W4200492323","https://openalex.org/W4214651231","https://openalex.org/W4230025303","https://openalex.org/W4237498818","https://openalex.org/W4237687284","https://openalex.org/W4242509916","https://openalex.org/W4242589337","https://openalex.org/W4249142012","https://openalex.org/W4254240460","https://openalex.org/W4282959339","https://openalex.org/W4283379731","https://openalex.org/W4288079579","https://openalex.org/W4288083766","https://openalex.org/W4293775467","https://openalex.org/W4293999362","https://openalex.org/W4312411608","https://openalex.org/W4312968147","https://openalex.org/W4387302738","https://openalex.org/W4387321109"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Adjusting":[0],"batch":[1,85],"sizes":[2],"and":[3,42,51,71,82,99,129],"adaptively":[4],"tuning":[5],"other":[6],"hyperparameters":[7],"can":[8],"significantly":[9],"speed":[10],"up":[11,119,130],"deep":[12],"neural":[13],"network":[14],"(DNN)":[15],"training.":[16],"Despite":[17],"the":[18,78,124],"ubiquity":[19],"of":[20],"heterogeneous":[21,37,92,116],"clusters,":[22],"existing":[23,45],"adaptive":[24,84,126],"DNN":[25,34,113],"training":[26,35,66,87,114,127],"techniques":[27,46],"solely":[28],"consider":[29],"homogeneous":[30],"environments.":[31],"Optimizing":[32],"distributed":[33,65],"over":[36,102],"clusters":[38,117],"is":[39],"technically":[40],"challenging,":[41],"directly":[43],"adapting":[44],"results":[47,108],"in":[48,91,97,105,115],"low":[49],"utilization":[50],"poor":[52],"performance.":[53],"To":[54],"solve":[55],"this":[56],"problem,":[57],"we":[58],"introduce":[59],"Cannikin":[60,68,96,111],"-":[61],"a":[62],"novel":[63],"data-parallel":[64],"system.":[67],"achieves":[69],"efficient":[70],"near":[72],"optimal":[73,79],"performance":[74,81],"by":[75,118],"accurately":[76],"modeling":[77],"system":[80,128],"predicting":[83],"size":[86],"metrics":[88],"for":[89],"DNNs":[90],"clusters.":[93],"We":[94],"implemented":[95],"PyTorch":[98,136],"conducted":[100],"experiments":[101],"16":[103],"GPUs":[104],"Chameleon.":[106],"Empirical":[107],"show":[109],"that":[110],"reduces":[112],"to":[120,123,131,134],"52%":[121],"compared":[122,133],"state-of-art":[125],"85%":[132],"native":[135],"DistributedDataParallel.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}