{"id":"https://openalex.org/W4409122647","doi":"https://doi.org/10.1109/hpec62836.2024.10938447","title":"A Dynamic Weighting Strategy to Mitigate Worker Node Failure in Distributed Deep Learning","display_name":"A Dynamic Weighting Strategy to Mitigate Worker Node Failure in Distributed Deep Learning","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4409122647","doi":"https://doi.org/10.1109/hpec62836.2024.10938447"},"language":"en","primary_location":{"id":"doi:10.1109/hpec62836.2024.10938447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5057982691","display_name":"Yuesheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuesheng Xu","raw_affiliation_strings":["Lehigh University,Computer Science & Engineering,Bethlehem,USA"],"affiliations":[{"raw_affiliation_string":"Lehigh University,Computer Science & Engineering,Bethlehem,USA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039776957","display_name":"Arielle Carr","orcid":"https://orcid.org/0000-0001-5827-0132"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arielle Carr","raw_affiliation_strings":["Lehigh University,Computer Science & Engineering,Bethlehem,USA"],"affiliations":[{"raw_affiliation_string":"Lehigh University,Computer Science & Engineering,Bethlehem,USA","institution_ids":["https://openalex.org/I186143895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057982691"],"corresponding_institution_ids":["https://openalex.org/I186143895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37936695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13812","display_name":"AI and HR Technologies","score":0.12409999966621399,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13812","display_name":"AI and HR Technologies","score":0.12409999966621399,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.7813705205917358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6605937480926514},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6388291120529175},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5157554149627686},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5143967270851135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43789932131767273},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13305652141571045},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.058201223611831665}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7813705205917358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6605937480926514},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6388291120529175},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5157554149627686},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5143967270851135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43789932131767273},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13305652141571045},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.058201223611831665},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec62836.2024.10938447","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5299999713897705,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W2068484625","https://openalex.org/W2108214478","https://openalex.org/W2112796928","https://openalex.org/W2167732364","https://openalex.org/W3031420959","https://openalex.org/W4244218767","https://openalex.org/W4406457811","https://openalex.org/W6604254268","https://openalex.org/W6631190155","https://openalex.org/W6638803421","https://openalex.org/W6684859321","https://openalex.org/W6703420464","https://openalex.org/W6727249380","https://openalex.org/W6743655711","https://openalex.org/W6800641243"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W3086377361"],"abstract_inverted_index":{"The":[0],"increasing":[1],"complexity":[2],"of":[3,14,19,72,83,94],"deep":[4,50],"learning":[5],"models":[6],"and":[7,39,57,81,96,104],"the":[8,17,58,70,79,84],"demand":[9],"for":[10,23],"processing":[11],"vast":[12],"amounts":[13],"data":[15],"make":[16],"utilization":[18],"large-scale":[20],"distributed":[21,49],"systems":[22],"efficient":[24],"training":[25,86],"essential.":[26],"These":[27],"systems,":[28],"however,":[29],"face":[30],"significant":[31],"challenges":[32],"such":[33],"as":[34],"communication":[35,97],"overhead,":[36],"hardware":[37],"limitations,":[38],"node":[40],"failure.":[41],"This":[42],"paper":[43],"investigates":[44],"various":[45],"optimization":[46],"techniques":[47],"in":[48],"learning,":[51],"including":[52],"Elastic":[53],"Averaging":[54],"SGD":[55],"(EASGD)":[56],"second-order":[59],"method":[60],"AdaHessian.":[61],"We":[62,88],"propose":[63],"a":[64],"dynamic":[65],"weighting":[66],"strategy":[67],"to":[68,76,99],"mitigate":[69],"problem":[71],"straggler":[73],"nodes":[74],"due":[75],"failure,":[77],"enhancing":[78],"performance":[80,106],"efficiency":[82],"overall":[85],"process.":[87],"conduct":[89],"experiments":[90],"with":[91],"different":[92],"numbers":[93],"workers":[95],"periods":[98],"demonstrate":[100],"improved":[101],"convergence":[102],"rates":[103],"test":[105],"using":[107],"our":[108],"strategy.":[109]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}