{"id":"https://openalex.org/W4405812329","doi":"https://doi.org/10.1109/tnse.2024.3523320","title":"A Dynamic Sliding Window Based Tensor Communication Scheduling Framework for Distributed Deep Learning","display_name":"A Dynamic Sliding Window Based Tensor Communication Scheduling Framework for Distributed Deep Learning","publication_year":2024,"publication_date":"2024-12-26","ids":{"openalex":"https://openalex.org/W4405812329","doi":"https://doi.org/10.1109/tnse.2024.3523320"},"language":"en","primary_location":{"id":"doi:10.1109/tnse.2024.3523320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2024.3523320","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"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 Network Science and Engineering","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/A5011127712","display_name":"Yunqi Gao","orcid":"https://orcid.org/0009-0003-0599-8383"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunqi Gao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-0599-8383","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102834373","display_name":"Bing Hu","orcid":"https://orcid.org/0000-0002-0594-8998"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Hu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0594-8998","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028862760","display_name":"Mahdi Boloursaz Mashhadi","orcid":"https://orcid.org/0000-0001-9948-9165"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mahdi Boloursaz Mashhadi","raw_affiliation_strings":["5GIC &amp; 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9948-9165","affiliations":[{"raw_affiliation_string":"5GIC &amp; 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392219","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0003-2153-9075"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2153-9075","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032549075","display_name":"Rahim Tafazolli","orcid":"https://orcid.org/0000-0002-6062-8639"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rahim Tafazolli","raw_affiliation_strings":["5GIC &amp; 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K"],"raw_orcid":"https://orcid.org/0000-0002-6062-8639","affiliations":[{"raw_affiliation_string":"5GIC &amp; 6GIC, Institute for Communication Systems (ICS), University of Surrey, Guildford, U.K","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056145687","display_name":"M\u00e9rouane Debbah","orcid":"https://orcid.org/0000-0001-8941-8080"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"M\u00e9rouane Debbah","raw_affiliation_strings":["KU 6G Research Center, Department of Computer and Information Engineering, Khalifa University, Abu Dhabi, UAE"],"raw_orcid":"https://orcid.org/0000-0001-8941-8080","affiliations":[{"raw_affiliation_string":"KU 6G Research Center, Department of Computer and Information Engineering, Khalifa University, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I176601375"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4087,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63025083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"12","issue":"2","first_page":"1080","last_page":"1095"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T12303","display_name":"Tensor decomposition and applications","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"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/computer-science","display_name":"Computer science","score":0.687614381313324},{"id":"https://openalex.org/keywords/sliding-window-protocol","display_name":"Sliding window protocol","score":0.61478590965271},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5107024312019348},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.43615058064460754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3481777310371399},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.2929236888885498},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2181619107723236},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13374751806259155}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687614381313324},{"id":"https://openalex.org/C102392041","wikidata":"https://www.wikidata.org/wiki/Q592860","display_name":"Sliding window protocol","level":3,"score":0.61478590965271},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5107024312019348},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.43615058064460754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3481777310371399},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2929236888885498},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2181619107723236},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13374751806259155},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnse.2024.3523320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2024.3523320","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"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 Network Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6284364839","display_name":null,"funder_award_id":"202406320382","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W114517082","https://openalex.org/W2057332538","https://openalex.org/W2083842231","https://openalex.org/W2108598243","https://openalex.org/W2186615578","https://openalex.org/W2194775991","https://openalex.org/W2896457183","https://openalex.org/W2920397365","https://openalex.org/W2947198853","https://openalex.org/W2963446712","https://openalex.org/W2969388332","https://openalex.org/W2973727699","https://openalex.org/W2975712713","https://openalex.org/W2991040477","https://openalex.org/W3030163527","https://openalex.org/W3047537431","https://openalex.org/W3086105743","https://openalex.org/W3172612645","https://openalex.org/W3177554119","https://openalex.org/W3188270315","https://openalex.org/W3193250980","https://openalex.org/W3203336515","https://openalex.org/W4283207077","https://openalex.org/W4283217358","https://openalex.org/W4301239768","https://openalex.org/W4387544258","https://openalex.org/W4388535823","https://openalex.org/W4388544075","https://openalex.org/W4390660070","https://openalex.org/W4401024791","https://openalex.org/W6637373629","https://openalex.org/W6676984168","https://openalex.org/W6679393576","https://openalex.org/W6686509673","https://openalex.org/W6687566353","https://openalex.org/W6713134421","https://openalex.org/W6739693220","https://openalex.org/W6746081298","https://openalex.org/W6746200960","https://openalex.org/W6748645090","https://openalex.org/W6754818105","https://openalex.org/W6760703128","https://openalex.org/W6762211661","https://openalex.org/W6766978945","https://openalex.org/W6767997687","https://openalex.org/W6769475105","https://openalex.org/W6794216301","https://openalex.org/W6797162769","https://openalex.org/W6799372109","https://openalex.org/W6839137647","https://openalex.org/W6845510308"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2353818951","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Simultaneous":[0],"tensor":[1,20,42,49],"communication":[2,32,43,79,89],"can":[3,143],"effectively":[4],"improve":[5],"the":[6,25,66,75,85,95,100,112,117,124,172],"scalability":[7],"of":[8,19,69,77,87,120,171],"distributed":[9,61],"deep":[10],"learning":[11],"on":[12,52,127,132],"large":[13],"clusters.":[14],"However,":[15],"a":[16,39,106],"fixed":[17],"number":[18],"blocks":[21,50],"communicated":[22],"concurrently":[23],"violates":[24],"priority-based":[26],"scheduling":[27],"strategy":[28],"and":[29,80,83,90,104,150,158,169,179],"cannot":[30],"minimize":[31,57],"overheads.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"propose":[38],"novel":[40],"simultaneous":[41],"framework,":[44],"namely":[45],"D-Credit,":[46],"which":[47],"transmits":[48],"based":[51],"dynamic":[53,113],"sliding":[54],"windows":[55],"to":[56,109,146,154,167,177],"per-iteration":[58],"time":[59],"in":[60,71],"DNN":[62],"training.":[63],"We":[64,93,122],"build":[65],"mathematical":[67],"model":[68],"D-Credit":[70,125,142,164],"two":[72,133],"phases:":[73],"(1)":[74],"overlap":[76,86],"gradient":[78,88],"backward":[81],"propagation,":[82],"(2)":[84],"forward":[91],"computation.":[92],"drive":[94],"optimal":[96],"window":[97,114],"sizes":[98,115],"for":[99,116],"second":[101],"phase":[102,119],"analytically,":[103],"develop":[105],"greedy":[107],"algorithm":[108],"efficiently":[110],"determine":[111],"first":[118],"D-Credit.":[121],"implement":[123],"architecture":[126],"PyTorch":[128],"framework.":[129],"Experimental":[130],"results":[131],"different":[134],"GPU":[135],"clusters":[136],"demonstrate":[137],"that":[138],"at":[139],"training":[140,173],"speed,":[141],"achieve":[144],"up":[145,166],"1.26x,":[147],"1.21x,":[148],"1.48x":[149],"1.53x":[151],"speedup":[152],"compared":[153,176],"ByteScheduler,":[155],"DeAR,":[156],"PyTorch-DDP":[157],"WFBP,":[159,180],"respectively.":[160,181],"At":[161],"energy":[162,174],"consumption,":[163],"saves":[165],"17.8%":[168],"25.1%":[170],"consumption":[175],"ByteScheduler":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
