{"id":"https://openalex.org/W3005780259","doi":"https://doi.org/10.1145/3377811.3380362","title":"An empirical study on program failures of deep learning jobs","display_name":"An empirical study on program failures of deep learning jobs","publication_year":2020,"publication_date":"2020-06-27","ids":{"openalex":"https://openalex.org/W3005780259","doi":"https://doi.org/10.1145/3377811.3380362","mag":"3005780259"},"language":"en","primary_location":{"id":"doi:10.1145/3377811.3380362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377811.3380362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering","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/A5100750676","display_name":"Ru Zhang","orcid":"https://orcid.org/0000-0001-8744-4525"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ru Zhang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086945155","display_name":"Wencong Xiao","orcid":"https://orcid.org/0000-0002-3043-522X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wencong Xiao","raw_affiliation_strings":["Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["The University of Newcastle"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Newcastle","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345786","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0002-5216-3181"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013547786","display_name":"Haoxiang Lin","orcid":"https://orcid.org/0000-0002-9148-5861"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haoxiang Lin","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438310","display_name":"Mao Yang","orcid":"https://orcid.org/0009-0009-6455-3898"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mao Yang","raw_affiliation_strings":["Microsoft Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.3487,"has_fulltext":false,"cited_by_count":99,"citation_normalized_percentile":{"value":0.9953164,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1159","last_page":"1170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9979000091552734,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9979000091552734,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9973999857902527,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.805679202079773},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7215016484260559},{"id":"https://openalex.org/keywords/productivity","display_name":"Productivity","score":0.5870657563209534},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.585793673992157},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.46276727318763733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4261905252933502},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.37114912271499634},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15302693843841553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.805679202079773},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7215016484260559},{"id":"https://openalex.org/C204983608","wikidata":"https://www.wikidata.org/wiki/Q2111958","display_name":"Productivity","level":2,"score":0.5870657563209534},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.585793673992157},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.46276727318763733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4261905252933502},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.37114912271499634},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15302693843841553},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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":2,"locations":[{"id":"doi:10.1145/3377811.3380362","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377811.3380362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:uon:38663","is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.13/1428865","pdf_url":null,"source":{"id":"https://openalex.org/S4377196471","display_name":"NOVA (University of Newcastle Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I78757542","host_organization_name":"University of Newcastle Australia","host_organization_lineage":["https://openalex.org/I78757542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1589576271","https://openalex.org/W1757796397","https://openalex.org/W1867761151","https://openalex.org/W2039676055","https://openalex.org/W2087419855","https://openalex.org/W2088727885","https://openalex.org/W2097117768","https://openalex.org/W2101512909","https://openalex.org/W2114053493","https://openalex.org/W2158698691","https://openalex.org/W2164948578","https://openalex.org/W2168206938","https://openalex.org/W2186615578","https://openalex.org/W2296335794","https://openalex.org/W2402144811","https://openalex.org/W2475334473","https://openalex.org/W2513383847","https://openalex.org/W2613904329","https://openalex.org/W2616028256","https://openalex.org/W2622263826","https://openalex.org/W2732547613","https://openalex.org/W2743948853","https://openalex.org/W2752512710","https://openalex.org/W2753713840","https://openalex.org/W2769279756","https://openalex.org/W2772678505","https://openalex.org/W2789444109","https://openalex.org/W2798515322","https://openalex.org/W2850992922","https://openalex.org/W2896457183","https://openalex.org/W2899071864","https://openalex.org/W2919594608","https://openalex.org/W2963150697","https://openalex.org/W2963327228","https://openalex.org/W2963403751","https://openalex.org/W2963403868","https://openalex.org/W2963785012","https://openalex.org/W2964174152","https://openalex.org/W2968594320","https://openalex.org/W2970971581","https://openalex.org/W3103894541","https://openalex.org/W4241104364","https://openalex.org/W4242010563","https://openalex.org/W4301361180"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2611989081","https://openalex.org/W2440403839","https://openalex.org/W599097301","https://openalex.org/W2731899572","https://openalex.org/W4230611425","https://openalex.org/W4294635752","https://openalex.org/W4304166257","https://openalex.org/W4383066092","https://openalex.org/W4366307084"],"abstract_inverted_index":{"Deep":[0],"learning":[1,24],"has":[2],"made":[3],"significant":[4],"achievements":[5],"in":[6],"many":[7],"application":[8],"areas.":[9],"To":[10],"train":[11],"and":[12,20,51,59],"test":[13],"models":[14],"more":[15],"efficiently,":[16],"enterprise":[17],"developers":[18],"submit":[19],"run":[21],"their":[22],"deep":[23],"programs":[25,35],"on":[26],"a":[27,38],"shared,":[28],"multi-tenant":[29],"platform.":[30],"However,":[31],"some":[32],"of":[33],"the":[34,48],"fail":[36],"after":[37],"long":[39],"execution":[40],"time":[41],"due":[42],"to":[43],"code/script":[44],"defects,":[45],"which":[46],"reduces":[47],"development":[49],"productivity":[50],"wastes":[52],"expensive":[53],"resources":[54],"such":[55],"as":[56],"GPU,":[57],"storage,":[58],"network":[60],"I/O.":[61]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}