{"id":"https://openalex.org/W7131650188","doi":"https://doi.org/10.1109/tr.2026.3668208","title":"Redundant Hierarchical Ring All-Reduce in Hypercubes","display_name":"Redundant Hierarchical Ring All-Reduce in Hypercubes","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131650188","doi":"https://doi.org/10.1109/tr.2026.3668208"},"language":null,"primary_location":{"id":"doi:10.1109/tr.2026.3668208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2026.3668208","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Reliability","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/A5051272519","display_name":"Huimei Guo","orcid":"https://orcid.org/0000-0002-5356-9060"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimei Guo","raw_affiliation_strings":["School of Mathematics and Statistics, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5356-9060","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040978935","display_name":"Shuo Quan","orcid":"https://orcid.org/0000-0001-8824-631X"},"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/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Quan","raw_affiliation_strings":["China Telecom Cloud Computing Research Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8824-631X","affiliations":[{"raw_affiliation_string":"China Telecom Cloud Computing Research Institute, Beijing, China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049116158","display_name":"Rong\u2010Xia Hao","orcid":"https://orcid.org/0000-0001-8714-8750"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong-Xia Hao","raw_affiliation_strings":["School of Mathematics and Statistics, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8714-8750","affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126858101","display_name":"Jie Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I84392919","display_name":"Temple University","ror":"https://ror.org/00kx1jb78","country_code":"US","type":"education","lineage":["https://openalex.org/I84392919"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["China Telecom Cloud Computing Research Institute and the Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3472-1717","affiliations":[{"raw_affiliation_string":"China Telecom Cloud Computing Research Institute and the Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I84392919"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.17210001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"75","issue":null,"first_page":"1350","last_page":"1364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.5986999869346619,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.5986999869346619,"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/T12541","display_name":"Graph Labeling and Dimension Problems","score":0.08380000293254852,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11703","display_name":"Rings, Modules, and Algebras","score":0.031300000846385956,"subfield":{"id":"https://openalex.org/subfields/2602","display_name":"Algebra and Number Theory"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hypercube","display_name":"Hypercube","score":0.7365999817848206},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5145000219345093},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4106000065803528},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.3887999951839447},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.3792000114917755},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.3553999960422516},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.3476000130176544}],"concepts":[{"id":"https://openalex.org/C50820777","wikidata":"https://www.wikidata.org/wiki/Q213723","display_name":"Hypercube","level":2,"score":0.7365999817848206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7226999998092651},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.439300000667572},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4253999888896942},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.3476000130176544},{"id":"https://openalex.org/C122306262","wikidata":"https://www.wikidata.org/wiki/Q719775","display_name":"Ring network","level":3,"score":0.3294000029563904},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.2924000024795532},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C167927819","wikidata":"https://www.wikidata.org/wiki/Q1930567","display_name":"Shuffling","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C130120984","wikidata":"https://www.wikidata.org/wiki/Q2835898","display_name":"Distributed algorithm","level":2,"score":0.2619999945163727}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tr.2026.3668208","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tr.2026.3668208","pdf_url":null,"source":{"id":"https://openalex.org/S87725633","display_name":"IEEE Transactions on Reliability","issn_l":"0018-9529","issn":["0018-9529","1558-1721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Reliability","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2501702286","display_name":null,"funder_award_id":"12471321","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"},{"id":"https://openalex.org/G3598992853","display_name":null,"funder_award_id":"12331013","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Distributed":[0],"training":[1],"of":[2,75,97,103,126],"large":[3],"language":[4],"models":[5],"demands":[6],"efficient":[7],"gradient":[8,127],"synchronization":[9,128],"strategies.":[10],"Existing":[11],"All":[12],"Reduce":[13],"algorithms":[14],"often":[15],"fail":[16],"to":[17,107,151],"fully":[18],"leverage":[19],"underlying":[20],"topological":[21],"properties,":[22],"resulting":[23],"in":[24,31,148],"low":[25],"edge":[26,59],"utilization":[27,60],"and":[28,68,100,111],"unbalanced":[29],"load":[30],"hypercube":[32,46],"networks.":[33],"This":[34],"paper":[35],"proposes":[36],"a":[37,52],"Redundant":[38],"Hierarchical":[39],"Ring":[40,54],"All-Reduce":[41,55],"(RHRA)":[42],"algorithm":[43,49,121],"tailored":[44],"for":[45],"topologies.":[47],"The":[48],"first":[50],"designs":[51],"hierarchical":[53,76],"structure":[56],"with":[57,134],"high":[58,66,157],"by":[61],"exploiting":[62],"the":[63,72,92,95,101,123],"hypercube's":[64],"inherent":[65],"parallelism":[67],"symmetry,":[69],"proving":[70],"that":[71,119],"optimal":[73],"number":[74,125],"layers":[77],"is":[78],"n":[79],"2.":[80],"It":[81],"then":[82],"introduces":[83],"controlled":[84],"redundancy,":[85],"dynamically":[86],"adjusting":[87],"transmission":[88,112,136],"strategies":[89],"based":[90],"on":[91],"relationship":[93],"between":[94],"value":[96,102],"bandwidth":[98,132],"B":[99],"data":[104],"volume":[105],"D":[106],"reduce":[108],"communication":[109],"hops":[110,129],"latency":[113],"while":[114,155],"ensuring":[115],"reliability.":[116,158],"Experiments":[117],"demonstrate":[118],"our":[120],"achieves":[122],"minimum":[124],"under":[130],"varying":[131],"constraints,":[133],"end-to-end":[135],"time":[137],"significantly":[138],"outperforming":[139],"existing":[140],"schemes.":[141],"Further":[142],"reliability":[143],"simulations":[144],"verify":[145],"its":[146],"effectiveness":[147],"balancing":[149],"redundancy":[150],"prevent":[152],"resource":[153],"waste":[154],"maintaining":[156]},"counts_by_year":[],"updated_date":"2026-03-31T06:02:25.137627","created_date":"2026-02-27T00:00:00"}
