{"id":"https://openalex.org/W7166591649","doi":"https://doi.org/10.1109/infocom59046.2026.11571695","title":"Rehabilitating over Recomputing: A Novel Failure Recovery Method for Large Model Training","display_name":"Rehabilitating over Recomputing: A Novel Failure Recovery Method for Large Model Training","publication_year":2026,"publication_date":"2026-05-18","ids":{"openalex":"https://openalex.org/W7166591649","doi":"https://doi.org/10.1109/infocom59046.2026.11571695"},"language":null,"primary_location":{"id":"doi:10.1109/infocom59046.2026.11571695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom59046.2026.11571695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","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/A5100784338","display_name":"Zichen Wang","orcid":"https://orcid.org/0000-0002-9369-6611"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichen Wang","raw_affiliation_strings":["Jilin University,College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University,College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065859286","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-9198-3951"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Li","raw_affiliation_strings":["Jilin University,College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University,College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139621030","display_name":"Jie Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]},{"id":"https://openalex.org/I4210144487","display_name":"Cloud Computing Center","ror":"https://ror.org/04aa0zm65","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210144487"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["China Telecom Cloud Computing Research Institute,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Cloud Computing Research Institute,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4210144487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139583049","display_name":"Zhewen Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhewen Xu","raw_affiliation_strings":["Jilin University,College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University,College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087484624","display_name":"Hairui Zhao","orcid":"https://orcid.org/0009-0008-7081-5172"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hairui Zhao","raw_affiliation_strings":["Jilin University,College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University,College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139580455","display_name":"Qi Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Jilin University,College of Computer Science and Technology,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University,College of Computer Science and Technology,China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017173606","display_name":"Haixiao Xu","orcid":"https://orcid.org/0009-0003-2143-2048"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haixiao Xu","raw_affiliation_strings":["Jilin University,High Performance Computing Center,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University,High Performance Computing Center,China","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77877966,"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":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.09059999883174896,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.09059999883174896,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.08489999920129776,"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":0.03680000081658363,"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/training","display_name":"Training (meteorology)","score":0.6169999837875366},{"id":"https://openalex.org/keywords/troubleshooting","display_name":"Troubleshooting","score":0.32109999656677246},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2906999886035919},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.25450000166893005}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6169999837875366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45170000195503235},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3303000032901764},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2939999997615814},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.24690000712871552},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.24289999902248383}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom59046.2026.11571695","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom59046.2026.11571695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310121","display_name":"Natural Science Foundation of Jilin Province","ror":null},{"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":24,"referenced_works":["https://openalex.org/W1586335931","https://openalex.org/W2033656974","https://openalex.org/W2798515322","https://openalex.org/W2962725887","https://openalex.org/W2963433607","https://openalex.org/W2998045710","https://openalex.org/W3081168214","https://openalex.org/W3129831491","https://openalex.org/W3132107458","https://openalex.org/W3204998121","https://openalex.org/W3206832494","https://openalex.org/W4250589301","https://openalex.org/W4289646389","https://openalex.org/W4385571616","https://openalex.org/W4387302750","https://openalex.org/W4387544258","https://openalex.org/W4394923484","https://openalex.org/W4404171822","https://openalex.org/W4404385781","https://openalex.org/W4406650295","https://openalex.org/W4407216788","https://openalex.org/W4408847328","https://openalex.org/W7084107549","https://openalex.org/W7133250524"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-06-30T00:00:00"}
