{"id":"https://openalex.org/W4411142984","doi":"https://doi.org/10.1109/tpds.2025.3577796","title":"ISACPP: Interference-Aware Scheduling Approach for Deep Learning Training Workloads Based on Co-Location Performance Prediction","display_name":"ISACPP: Interference-Aware Scheduling Approach for Deep Learning Training Workloads Based on Co-Location Performance Prediction","publication_year":2025,"publication_date":"2025-06-09","ids":{"openalex":"https://openalex.org/W4411142984","doi":"https://doi.org/10.1109/tpds.2025.3577796"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2025.3577796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3577796","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","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/A5002918928","display_name":"Zijie Liu","orcid":"https://orcid.org/0000-0003-4688-115X"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Liu","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-4688-115X","affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114514400","display_name":"Yi Cheng","orcid":"https://orcid.org/0009-0001-6940-7453"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cheng","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0001-6940-7453","affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101419943","display_name":"Can Chen","orcid":"https://orcid.org/0000-0002-1321-9672"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Chen","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071056908","display_name":"Jun Hu","orcid":"https://orcid.org/0000-0002-7852-5064"},"institutions":[{"id":"https://openalex.org/I4210154323","display_name":"China Central Television","ror":"https://ror.org/059h8x781","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210154323"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Hu","raw_affiliation_strings":["Jiangsu Cable Television Research Institute, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Cable Television Research Institute, Nanjing, China","institution_ids":["https://openalex.org/I4210154323"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rongguo Fu","orcid":"https://orcid.org/0009-0003-6400-246X"},"institutions":[{"id":"https://openalex.org/I4210100745","display_name":"Heilongjiang Earthquake Agency","ror":"https://ror.org/0146tv827","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210100745","https://openalex.org/I90149893"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongguo Fu","raw_affiliation_strings":["Jiangsu Earthquake Agency, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-6400-246X","affiliations":[{"raw_affiliation_string":"Jiangsu Earthquake Agency, Nanjing, China","institution_ids":["https://openalex.org/I4210100745"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076984228","display_name":"Dengyin Zhang","orcid":"https://orcid.org/0000-0001-6080-6151"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengyin Zhang","raw_affiliation_strings":["School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6080-6151","affiliations":[{"raw_affiliation_string":"School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"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":0.15288178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"8","first_page":"1591","last_page":"1607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9235000014305115,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9235000014305115,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8882313370704651},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6724201440811157},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5184568762779236},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.45971018075942993},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44953683018684387},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance prediction","score":0.44849893450737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42013949155807495},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.41856950521469116},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.36593231558799744},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34726017713546753},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.33292096853256226},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.1958218216896057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8882313370704651},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6724201440811157},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5184568762779236},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.45971018075942993},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44953683018684387},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.44849893450737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42013949155807495},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.41856950521469116},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.36593231558799744},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34726017713546753},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33292096853256226},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.1958218216896057},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"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:10.1109/tpds.2025.3577796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3577796","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4439784669","display_name":"\u57fa\u4e8e\u6df1\u5ea6\u5b66\u4e60\u7684\u5927\u6c14\u6563\u5c04\u65b0\u6a21\u578b\u4e0e\u56fe\u50cf\u53bb\u96fe\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61872423","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1586201613","https://openalex.org/W1689909837","https://openalex.org/W2105947650","https://openalex.org/W2194775991","https://openalex.org/W2290712622","https://openalex.org/W2302255633","https://openalex.org/W2331143823","https://openalex.org/W2464708700","https://openalex.org/W2531409750","https://openalex.org/W2549139847","https://openalex.org/W2752782242","https://openalex.org/W2798515322","https://openalex.org/W2903485826","https://openalex.org/W2934208298","https://openalex.org/W2963125010","https://openalex.org/W2963446712","https://openalex.org/W2964081807","https://openalex.org/W2964137095","https://openalex.org/W2975712713","https://openalex.org/W3012121966","https://openalex.org/W3012536640","https://openalex.org/W3036527662","https://openalex.org/W3093580137","https://openalex.org/W3094979069","https://openalex.org/W3106910749","https://openalex.org/W3132455321","https://openalex.org/W3133933212","https://openalex.org/W3135013702","https://openalex.org/W3136752701","https://openalex.org/W3157306683","https://openalex.org/W3171884590","https://openalex.org/W3210784622","https://openalex.org/W4205916020","https://openalex.org/W4206790491","https://openalex.org/W4246193833","https://openalex.org/W4253824360","https://openalex.org/W4285524851","https://openalex.org/W4286307983","https://openalex.org/W4290991121","https://openalex.org/W4294982491","https://openalex.org/W4312210066","https://openalex.org/W4315473450","https://openalex.org/W4317935380","https://openalex.org/W4319068657","https://openalex.org/W4320024258","https://openalex.org/W4376454504","https://openalex.org/W4383899813","https://openalex.org/W4385245566","https://openalex.org/W4387042170","https://openalex.org/W4388031348","https://openalex.org/W4388153979","https://openalex.org/W4388855511","https://openalex.org/W4388855529","https://openalex.org/W4388966802","https://openalex.org/W4391128621","https://openalex.org/W4404658388","https://openalex.org/W6637373629","https://openalex.org/W6695314431","https://openalex.org/W6727690538","https://openalex.org/W6737664043","https://openalex.org/W6755207826","https://openalex.org/W6758283263","https://openalex.org/W6759814162","https://openalex.org/W6778371292","https://openalex.org/W6784871562","https://openalex.org/W6785429063","https://openalex.org/W6801004768","https://openalex.org/W6802470573","https://openalex.org/W6811928498","https://openalex.org/W7067822191"],"related_works":["https://openalex.org/W2128410848","https://openalex.org/W2118368532","https://openalex.org/W2102390841","https://openalex.org/W3047653192","https://openalex.org/W2096289371","https://openalex.org/W2126232624","https://openalex.org/W2434525066","https://openalex.org/W3140149227","https://openalex.org/W2946406471","https://openalex.org/W2130555437"],"abstract_inverted_index":{"Traditional":[0],"exclusive":[1],"cloud":[2],"resource":[3,19,31],"allocation":[4],"for":[5,13,61,154],"deep":[6],"learning":[7],"training":[8],"(DLT)":[9],"workloads":[10,63,143],"is":[11,104],"unsuitable":[12],"advanced":[14],"GPU":[15,87,123,157,161],"infrastructure,":[16],"leading":[17],"to":[18,29,39,92,120,173,176],"under-utilization.":[20],"Fortunately,":[21],"DLT":[22,44,62,142],"workload":[23,35,103,169],"co-location":[24,36,66,94,98,110,118,139],"provides":[25],"a":[26,108,145],"promising":[27],"way":[28],"improve":[30],"utilization.":[32],"However,":[33],"existing":[34],"methods":[37],"fail":[38],"accurately":[40,136],"quantify":[41],"interference":[42,111],"among":[43],"workloads,":[45],"resulting":[46],"in":[47],"performance":[48,67,119,140],"degradation.":[49],"To":[50],"address":[51],"this":[52,54],"problem,":[53],"paper":[55],"proposes":[56,107],"an":[57,74],"interference-aware":[58,178],"scheduling":[59,179],"approach":[60],"based":[64],"on":[65],"prediction,":[68],"dubbed":[69],"\u2018ISACPP\u2019.":[70],"ISACPP":[71,106,134,165],"first":[72],"builds":[73],"edge-fusion":[75],"gated":[76],"graph":[77],"attention":[78],"network":[79],"(E-GGAT)":[80],"that":[81,133],"incorporates":[82],"DL":[83],"model":[84,113],"structures,":[85],"underlying":[86],"types,":[88],"and":[89,152,160],"hyper-parameter":[90],"settings":[91],"predict":[93],"performance.":[95],"Since":[96],"the":[97,116,122,126,138],"state":[99],"changes":[100],"as":[101],"each":[102],"completed,":[105],"multi-stage":[109],"quantification":[112],"derived":[114],"from":[115],"predicted":[117],"identify":[121],"device":[124],"with":[125,144],"minimum":[127],"overall":[128],"interference.":[129],"Experimental":[130],"results":[131],"demonstrate":[132],"can":[135,166],"estimate":[137],"of":[141,149],"maximum":[146],"prediction":[147],"error":[148],"8.72%,":[150],"1.9%,":[151],"4.4%":[153],"execution":[155],"time,":[156],"memory":[158],"consumption,":[159],"utilization,":[162],"respectively.":[163],"Meanwhile,":[164],"significantly":[167],"shorten":[168],"makespan":[170],"by":[171],"up":[172],"34.9%":[174],"compared":[175],"state-of-the-art":[177],"methods.":[180]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}