{"id":"https://openalex.org/W4395020669","doi":"https://doi.org/10.1145/3620665.3640375","title":"Heet: Accelerating Elastic Training in Heterogeneous Deep Learning Clusters","display_name":"Heet: Accelerating Elastic Training in Heterogeneous Deep Learning Clusters","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4395020669","doi":"https://doi.org/10.1145/3620665.3640375"},"language":"en","primary_location":{"id":"doi:10.1145/3620665.3640375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620665.3640375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","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/A5005355007","display_name":"Zizhao Mo","orcid":"https://orcid.org/0000-0002-3590-4400"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Zizhao Mo","raw_affiliation_strings":["University of Macau, Macau SAR, China, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0002-3590-4400","affiliations":[{"raw_affiliation_string":"University of Macau, Macau SAR, China, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017636962","display_name":"Huanle Xu","orcid":"https://orcid.org/0000-0001-6657-1154"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Huanle Xu","raw_affiliation_strings":["University of Macau, Macau SAR, China, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0001-6657-1154","affiliations":[{"raw_affiliation_string":"University of Macau, Macau SAR, China, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012773300","display_name":"Chengzhong Xu","orcid":"https://orcid.org/0000-0001-9480-0356"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Chengzhong Xu","raw_affiliation_strings":["University of Macau, Macau SAR, China, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0001-9480-0356","affiliations":[{"raw_affiliation_string":"University of Macau, Macau SAR, China, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005355007"],"corresponding_institution_ids":["https://openalex.org/I204512498"],"apc_list":null,"apc_paid":null,"fwci":4.967,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95650859,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"499","last_page":"513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9988999962806702,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9988999962806702,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7693210244178772},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.632208526134491},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6090553402900696},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6071071028709412},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5086720585823059},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5078778862953186},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4188682436943054},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37975457310676575},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16472169756889343},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.13701090216636658},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07188144326210022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7693210244178772},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.632208526134491},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6090553402900696},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6071071028709412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5086720585823059},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5078778862953186},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4188682436943054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37975457310676575},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16472169756889343},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.13701090216636658},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07188144326210022},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620665.3640375","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620665.3640375","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W114517082","https://openalex.org/W1993343369","https://openalex.org/W2123504579","https://openalex.org/W2132022337","https://openalex.org/W2133569115","https://openalex.org/W2134584261","https://openalex.org/W2885836230","https://openalex.org/W2899071864","https://openalex.org/W2901299405","https://openalex.org/W2910100551","https://openalex.org/W2911382970","https://openalex.org/W2914209329","https://openalex.org/W2919594608","https://openalex.org/W2926767350","https://openalex.org/W2969388332","https://openalex.org/W2970971581","https://openalex.org/W2982356264","https://openalex.org/W3011751313","https://openalex.org/W3022298203","https://openalex.org/W3022548332","https://openalex.org/W3037519745","https://openalex.org/W3047010778","https://openalex.org/W3080451848","https://openalex.org/W3095922049","https://openalex.org/W3097108668","https://openalex.org/W3101708369","https://openalex.org/W3106803824","https://openalex.org/W3130934537","https://openalex.org/W3132107458","https://openalex.org/W3154142431","https://openalex.org/W3188065709","https://openalex.org/W3197816522","https://openalex.org/W3204998121","https://openalex.org/W3209503812","https://openalex.org/W4230432948","https://openalex.org/W4236491543","https://openalex.org/W4240666298","https://openalex.org/W4253824360","https://openalex.org/W4288079579","https://openalex.org/W4291961336","https://openalex.org/W4312060029","https://openalex.org/W4318541537","https://openalex.org/W4318541676","https://openalex.org/W4372262787","https://openalex.org/W6675061135","https://openalex.org/W6779740189","https://openalex.org/W7067822191"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W141820298","https://openalex.org/W2049584446","https://openalex.org/W2079781215","https://openalex.org/W4378770497","https://openalex.org/W4308245303","https://openalex.org/W2014033564","https://openalex.org/W2910573937","https://openalex.org/W4385571583","https://openalex.org/W4389519396"],"abstract_inverted_index":{"Modern":[0],"GPU":[1],"clusters":[2],"inherently":[3],"exhibit":[4],"heterogeneity,":[5],"encompassing":[6],"various":[7],"aspects":[8],"such":[9],"as":[10],"computation":[11],"and":[12],"communication.":[13],"This":[14],"heterogeneity":[15,37],"poses":[16],"a":[17],"significant":[18],"challenge":[19],"for":[20],"the":[21,34],"elastic":[22,30],"scheduling":[23],"of":[24,36],"deep":[25],"learning":[26],"workloads.":[27],"Unfortunately,":[28],"existing":[29],"schedulers":[31],"often":[32],"overlook":[33],"impact":[35],"on":[38],"scaling":[39],"efficiency,":[40],"resulting":[41],"in":[42],"considerably":[43],"prolonged":[44],"job":[45],"completion":[46],"times.":[47]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}