{"id":"https://openalex.org/W4401942800","doi":"https://doi.org/10.1109/tdsc.2024.3450951","title":"An Automated Monitoring and Repairing System for DNN Training","display_name":"An Automated Monitoring and Repairing System for DNN Training","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4401942800","doi":"https://doi.org/10.1109/tdsc.2024.3450951"},"language":"en","primary_location":{"id":"doi:10.1109/tdsc.2024.3450951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tdsc.2024.3450951","pdf_url":null,"source":{"id":"https://openalex.org/S133795288","display_name":"IEEE Transactions on Dependable and Secure Computing","issn_l":"1545-5971","issn":["1545-5971","1941-0018","2160-9209"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Dependable and Secure Computing","raw_type":"journal-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/A5092424261","display_name":"Xiaoyu Zhang","orcid":"https://orcid.org/0000-0001-7010-6749"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Zhang","raw_affiliation_strings":["School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7010-6749","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101843177","display_name":"Chao Shen","orcid":"https://orcid.org/0000-0002-6959-0569"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Shen","raw_affiliation_strings":["School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6959-0569","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shiqing Ma","orcid":"https://orcid.org/0000-0003-1551-8948"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqing Ma","raw_affiliation_strings":["Manning College of Information & Computer Sciences, University of Massachusetts, Amherst, MA, USA","Manning College of Information & Computer Sciences, University of Massachusetts, Amherst, USA"],"raw_orcid":"https://orcid.org/0000-0003-1551-8948","affiliations":[{"raw_affiliation_string":"Manning College of Information & Computer Sciences, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]},{"raw_affiliation_string":"Manning College of Information & Computer Sciences, University of Massachusetts, Amherst, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071575216","display_name":"Juan Zhai","orcid":"https://orcid.org/0000-0001-5017-8016"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan Zhai","raw_affiliation_strings":["Manning College of Information & Computer Sciences, University of Massachusetts, Amherst, MA, USA","Manning College of Information & Computer Sciences, University of Massachusetts, Amherst, USA"],"raw_orcid":"https://orcid.org/0000-0001-5017-8016","affiliations":[{"raw_affiliation_string":"Manning College of Information & Computer Sciences, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]},{"raw_affiliation_string":"Manning College of Information & Computer Sciences, University of Massachusetts, Amherst, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046723920","display_name":"Chenhao Lin","orcid":"https://orcid.org/0000-0002-6265-7345"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenhao Lin","raw_affiliation_strings":["School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China","School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6265-7345","affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44005872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"22","issue":"2","first_page":"1655","last_page":"1673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.38359999656677246,"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"}},"topics":[{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.38359999656677246,"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/computer-science","display_name":"Computer science","score":0.7257190942764282},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6112205982208252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41116097569465637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257190942764282},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6112205982208252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41116097569465637},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tdsc.2024.3450951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tdsc.2024.3450951","pdf_url":null,"source":{"id":"https://openalex.org/S133795288","display_name":"IEEE Transactions on Dependable and Secure Computing","issn_l":"1545-5971","issn":["1545-5971","1941-0018","2160-9209"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Dependable and Secure Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2318223147","display_name":null,"funder_award_id":"62006181","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2528846581","display_name":null,"funder_award_id":"62161160337","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6034313629","display_name":null,"funder_award_id":"U21B2018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7155321176","display_name":null,"funder_award_id":"62132011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7948491709","display_name":null,"funder_award_id":"62206217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8024709401","display_name":null,"funder_award_id":"U20A20177","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1806891645","https://openalex.org/W1950843348","https://openalex.org/W1980287119","https://openalex.org/W2063387237","https://openalex.org/W2112796928","https://openalex.org/W2122947685","https://openalex.org/W2134734244","https://openalex.org/W2135198734","https://openalex.org/W2183640761","https://openalex.org/W2605516844","https://openalex.org/W2616028256","https://openalex.org/W2739781989","https://openalex.org/W2767431443","https://openalex.org/W2805627121","https://openalex.org/W2898868990","https://openalex.org/W2919115771","https://openalex.org/W2922301133","https://openalex.org/W2957905354","https://openalex.org/W2963913218","https://openalex.org/W2964024268","https://openalex.org/W3013948624","https://openalex.org/W3031251962","https://openalex.org/W3090898103","https://openalex.org/W3096533519","https://openalex.org/W3105249702","https://openalex.org/W3134686229","https://openalex.org/W3134796670","https://openalex.org/W3160369295","https://openalex.org/W3204610735","https://openalex.org/W3208407575","https://openalex.org/W3217530062","https://openalex.org/W4284666365","https://openalex.org/W4284681038","https://openalex.org/W4284701600","https://openalex.org/W4294214983","https://openalex.org/W4318577470","https://openalex.org/W4391579642","https://openalex.org/W4404107888","https://openalex.org/W6604254268","https://openalex.org/W6607862964","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6637381549","https://openalex.org/W6638273328","https://openalex.org/W6638545294","https://openalex.org/W6638667902","https://openalex.org/W6694517276","https://openalex.org/W6697966207","https://openalex.org/W6727249380","https://openalex.org/W6739879593","https://openalex.org/W6745899486","https://openalex.org/W6746023985","https://openalex.org/W6748413619","https://openalex.org/W6750964650","https://openalex.org/W6751923770","https://openalex.org/W6755207826","https://openalex.org/W6756887525","https://openalex.org/W6757170499","https://openalex.org/W6761469101","https://openalex.org/W6761471028","https://openalex.org/W6763194189","https://openalex.org/W6772859082","https://openalex.org/W6777581048","https://openalex.org/W6788811087","https://openalex.org/W6790608362","https://openalex.org/W6811340617"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2376932109"],"abstract_inverted_index":{"With":[0],"the":[1,21,27,38,46,73,100,112,128,142,161],"widespread":[2],"adoption":[3],"of":[4,17,155],"machine":[5],"learning":[6],"models,":[7,69],"especially":[8],"deep":[9],"neural":[10],"networks":[11],"(DNNs),":[12],"as":[13],"an":[14,86],"integral":[15],"part":[16],"new":[18,22],"intelligent":[19],"software,":[20],"tools":[23,40,53],"to":[24,56,124],"effectively":[25],"support":[26,44],"model":[28,101,162],"engineering":[29],"and":[30,64,76,89,104,115,137,159],"debugging":[31],"process":[32,103,114],"have":[33],"received":[34],"extensive":[35],"attention.":[36],"However,":[37],"existing":[39],"only":[41],"provide":[42],"limited":[43],"for":[45,92,99],"training":[47,67,74,102,110,113,118],"process.":[48],"They":[49],"are":[50],"either":[51],"post-training":[52],"that":[54,141],"fail":[55],"detect":[57],"problems":[58,158],"timely,":[59],"resulting":[60],"in":[61],"wasting":[62],"time":[63],"resources":[65],"on":[66,134,166],"buggy":[68],"or":[70],"merely":[71],"collecting":[72],"data":[75],"still":[77],"require":[78],"manual":[79],"analysis.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84],"proposeAutoTrainer,":[85],"automated":[87],"monitoring":[88,98],"repairing":[90],"system":[91],"DNN":[93],"training,":[94],"which":[95],"provides":[96],"real-time":[97],"automatically":[105],"repairs":[106],"eight":[107],"commonly":[108],"seen":[109],"problems.AutoTrainermonitors":[111],"detects":[116],"potential":[117],"problems.":[119],"For":[120],"any":[121],"detected":[122,157],"problem,AutoTrainertries":[123],"fix":[125],"it":[126,152],"with":[127],"built-in":[129],"state-of-the-art":[130],"solutions.":[131],"Our":[132],"experiments":[133],"six":[135],"datasets":[136],"701":[138],"models":[139],"show":[140],"problem":[143],"detection":[144],"accuracy":[145,163],"ofAutoTrainerreaches":[146],"100%":[147],"without":[148],"false":[149],"positives.":[150],"Moreover,":[151],"fixes":[153],"98.42%":[154],"all":[156],"improves":[160],"by":[164],"36.42%":[165],"average.":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}