{"id":"https://openalex.org/W7124205498","doi":"https://doi.org/10.1109/icpads67057.2025.11322964","title":"Classifying Host-Side RDMA Pingmesh Results to Efficiently Identify Transport Faults in Data Centers","display_name":"Classifying Host-Side RDMA Pingmesh Results to Efficiently Identify Transport Faults in Data Centers","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124205498","doi":"https://doi.org/10.1109/icpads67057.2025.11322964"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11322964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11322964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5123003919","display_name":"Songhao Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songhao Ding","raw_affiliation_strings":["Research Center for High-Efficiency Computing Infrastructure,Zhejiang Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for High-Efficiency Computing Infrastructure,Zhejiang Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646070","display_name":"Boyang Zhou","orcid":"https://orcid.org/0000-0003-0436-4293"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyang Zhou","raw_affiliation_strings":["Research Center for High-Efficiency Computing Infrastructure,Zhejiang Lab,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for High-Efficiency Computing Infrastructure,Zhejiang Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034102600","display_name":"Yuhua Zheng","orcid":"https://orcid.org/0000-0002-0977-5115"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]},{"id":"https://openalex.org/I4210137766","display_name":"Institute for Advanced Study","ror":"https://ror.org/03xg85719","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210137766"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Yuhua Zheng","raw_affiliation_strings":["School of Intelligent Science and Technology, Hangzhou Institute for Advanced Study, UCAS,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligent Science and Technology, Hangzhou Institute for Advanced Study, UCAS,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185","https://openalex.org/I4210137766"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.7592999935150146,"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":0.7592999935150146,"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":0.12129999697208405,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.009200000204145908,"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/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.916700005531311},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5205000042915344},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.4066999852657318},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.39480000734329224},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3926999866962433},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3587000072002411},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.35199999809265137},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3359000086784363}],"concepts":[{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.916700005531311},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7709000110626221},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4706000089645386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4255000054836273},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.4066999852657318},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3926999866962433},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C133320665","wikidata":"https://www.wikidata.org/wiki/Q179299","display_name":"RAID","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29319998621940613},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11322964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11322964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7166385407","display_name":null,"funder_award_id":"2024YFB4505604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2498764059","https://openalex.org/W2552554409","https://openalex.org/W2557879050","https://openalex.org/W2606788990","https://openalex.org/W2891570868","https://openalex.org/W2903266766","https://openalex.org/W2909113638","https://openalex.org/W2982355056","https://openalex.org/W3122026038","https://openalex.org/W3161507710","https://openalex.org/W4230300228","https://openalex.org/W4240522432","https://openalex.org/W4245040028","https://openalex.org/W4304820468","https://openalex.org/W4320001385","https://openalex.org/W4394744126","https://openalex.org/W4395073435","https://openalex.org/W4396680554","https://openalex.org/W4400233727","https://openalex.org/W4400236714","https://openalex.org/W4400678983","https://openalex.org/W4401175863","https://openalex.org/W4401176590","https://openalex.org/W4401176799","https://openalex.org/W4404011875","https://openalex.org/W4406472599","https://openalex.org/W4407783534","https://openalex.org/W4413756477","https://openalex.org/W4413756585","https://openalex.org/W7084065992"],"related_works":[],"abstract_inverted_index":{"To":[0,50,79],"diagnose":[1],"the":[2,9,16,28,34,52,71,81,84,93,97,102,185],"transport-layer":[3,115,163,190],"fault":[4,35,59,67,116,127],"in":[5,39,83],"RDMA":[6,18,114,162,189],"for":[7,42,76,156,184],"ensuring":[8],"reliability":[10],"of":[11,31,73,125,141,149,161,188],"data":[12,48,94,153],"center":[13],"networks":[14],"(DCN),":[15],"existing":[17],"pingmesh":[19],"(R-Pingmesh)":[20],"technology":[21],"often":[22],"requires":[23],"manual":[24],"analysis":[25],"to":[26,69,99,101,135],"identify":[27],"root":[29],"causes":[30],"faults.":[32,78,164,191],"However,":[33],"identification":[36],"faces":[37],"challenges":[38,148],"few-shot":[40,74,150],"training":[41,75],"rare":[43,77],"faults":[44],"and":[45,129,143,159],"prominent":[46],"fault-normal":[47],"imbalance.":[49],"address":[51],"challenges,":[53],"this":[54,110,169],"paper":[55],"proposes":[56],"an":[57,180],"LSTMbased":[58],"classifier:":[60],"The":[61],"model":[62,82],"pre-training":[63,142],"phase":[64],"captures":[65],"general":[66],"patterns":[68],"alleviate":[70],"difficulty":[72],"deploy":[80],"target":[85],"DCN,":[86,178],"it":[87],"uses":[88],"supervised":[89],"fine-tuning":[90],"(SFT)":[91],"with":[92],"obtained":[95],"from":[96,132,175],"network":[98,104,120],"adapt":[100],"different":[103,176],"topological":[105],"characteristics.":[106],"Through":[107],"such":[108],"training,":[109],"classifier":[111],"enables":[112],"finegrained":[113],"diagnosis":[117,187],"across":[118],"multiple":[119],"topologies,":[121],"achieving":[122],"accurate":[123,157],"classification":[124],"various":[126],"types":[128],"fine-grained":[130],"localization":[131,160],"\u201cabnormal":[133],"paths\u201d":[134],"\u201cfault":[136],"segments\u201d.":[137],"This":[138],"collaborative":[139],"design":[140],"topology":[144],"adaptation":[145],"achieves":[146],"key":[147],"learning":[151],"under":[152],"distribution":[154],"imbalance":[155],"distinction":[158],"Our":[165],"experiments":[166],"show":[167],"that":[168],"method":[170],"performs":[171],"excellently":[172],"on":[173],"datasets":[174],"typical":[177],"providing":[179],"effective":[181],"technical":[182],"solution":[183],"automated":[186]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-15T00:00:00"}