{"id":"https://openalex.org/W4413756918","doi":"https://doi.org/10.1145/3718958.3750513","title":"SkeletonHunter: Diagnosing and Localizing Network Failures in Containerized Large Model Training","display_name":"SkeletonHunter: Diagnosing and Localizing Network Failures in Containerized Large Model Training","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413756918","doi":"https://doi.org/10.1145/3718958.3750513"},"language":"en","primary_location":{"id":"doi:10.1145/3718958.3750513","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718958.3750513","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3718958.3750513","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2025 Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3718958.3750513","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100745747","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-9104-6316"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China","Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9104-6316","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008523628","display_name":"Kun Qian","orcid":"https://orcid.org/0000-0001-9882-9279"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Qian","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9882-9279","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357922","display_name":"Zhenhua Li","orcid":"https://orcid.org/0000-0001-7286-122X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7286-122X","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027605695","display_name":"Tianyin Xu","orcid":"https://orcid.org/0000-0003-4443-8170"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyin Xu","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Champaign, USA"],"raw_orcid":"https://orcid.org/0000-0003-4443-8170","affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110147702","display_name":"Yunhao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-5850-7132","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Weicheng Wang","orcid":"https://orcid.org/0009-0008-1785-448X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weicheng Wang","raw_affiliation_strings":["Alibaba Cloud, Hang Zhou, China"],"raw_orcid":"https://orcid.org/0009-0008-1785-448X","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hang Zhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yun Zhang","orcid":"https://orcid.org/0009-0008-9946-3641"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Zhang","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9946-3641","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiakang Li","orcid":"https://orcid.org/0009-0002-1155-1871"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiakang Li","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-1155-1871","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084079048","display_name":"Shuhong Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhong Zhu","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5404-797X","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677771","display_name":"Xue Li","orcid":"https://orcid.org/0000-0001-5713-7225"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Li","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5713-7225","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hongfei Xu","orcid":"https://orcid.org/0009-0000-2496-0661"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongfei Xu","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2496-0661","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Fei Feng","orcid":"https://orcid.org/0009-0001-2679-4983"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Feng","raw_affiliation_strings":["Alibaba Cloud, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2679-4983","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103040133","display_name":"Ennan Zhai","orcid":"https://orcid.org/0000-0003-4352-7497"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ennan Zhai","raw_affiliation_strings":["Alibaba Cloud, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4352-7497","affiliations":[{"raw_affiliation_string":"Alibaba Cloud, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"527","last_page":"540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9998999834060669,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9991000294685364,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6594060063362122},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6576206684112549},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.36037319898605347},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13972169160842896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6594060063362122},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6576206684112549},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.36037319898605347},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13972169160842896},{"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:10.1145/3718958.3750513","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718958.3750513","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3718958.3750513","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2025 Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3718958.3750513","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3718958.3750513","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3718958.3750513","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGCOMM 2025 Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4308740167","display_name":null,"funder_award_id":"62332012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4677586662","display_name":null,"funder_award_id":"62472245","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7634420332","display_name":null,"funder_award_id":"2022YFB4500703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413756918.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W169622638","https://openalex.org/W1511751337","https://openalex.org/W1543543926","https://openalex.org/W1990249073","https://openalex.org/W1997654368","https://openalex.org/W2048335062","https://openalex.org/W2063615912","https://openalex.org/W2065219958","https://openalex.org/W2115144768","https://openalex.org/W2126830184","https://openalex.org/W2146012756","https://openalex.org/W2158703410","https://openalex.org/W2487095677","https://openalex.org/W2498764059","https://openalex.org/W3046238985","https://openalex.org/W3046744974","https://openalex.org/W3046750740","https://openalex.org/W3091097978","https://openalex.org/W3197720002","https://openalex.org/W3204998121","https://openalex.org/W4225528709","https://openalex.org/W4254182148","https://openalex.org/W4290990900","https://openalex.org/W4380881087","https://openalex.org/W4386348926","https://openalex.org/W4386378069","https://openalex.org/W4386396242","https://openalex.org/W4386396590","https://openalex.org/W4386396783","https://openalex.org/W4401175863","https://openalex.org/W4401176521","https://openalex.org/W4401176590","https://openalex.org/W4401176593","https://openalex.org/W4401176799","https://openalex.org/W4402671178","https://openalex.org/W4404400565","https://openalex.org/W4404784329","https://openalex.org/W4409248703","https://openalex.org/W4411486137"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"The":[0],"flexibility":[1],"and":[2,45,48,55],"portability":[3],"characteristics":[4],"have":[5],"made":[6],"containers":[7],"a":[8],"popular":[9],"serverless":[10],"environment":[11],"for":[12,26],"large":[13,28],"model":[14,29],"training":[15,30],"in":[16,75],"recent":[17],"years.":[18],"Unfortunately,":[19],"these":[20],"advantages":[21],"render":[22],"the":[23,35,40,49],"network":[24,60],"support":[25],"containerized":[27],"extremely":[31],"challenging,":[32],"due":[33],"to":[34],"high":[36],"dynamics":[37],"of":[38],"containers,":[39],"complex":[41],"interplay":[42],"between":[43],"underlay":[44],"overlay":[46],"networks,":[47],"stringent":[50],"requirements":[51],"on":[52,65],"failure":[53],"detection":[54],"localization.":[56],"Existing":[57],"data":[58],"center":[59],"debugging":[61],"tools,":[62],"which":[63],"rely":[64],"comprehensive":[66],"or":[67,73],"opportunistic":[68],"monitoring,":[69],"are":[70],"either":[71],"inefficient":[72],"inaccurate":[74],"this":[76],"setting.":[77]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
