{"id":"https://openalex.org/W7125951651","doi":"https://doi.org/10.1109/smc58881.2025.11343203","title":"OLMP: Operator-Level Computational Graph Partition Mapping for Deep Learning","display_name":"OLMP: Operator-Level Computational Graph Partition Mapping for Deep Learning","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125951651","doi":"https://doi.org/10.1109/smc58881.2025.11343203"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5124121709","display_name":"Zhengyu Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhengyu Liu","raw_affiliation_strings":["Information Engineering University,Zhengzhou,China,450000"],"affiliations":[{"raw_affiliation_string":"Information Engineering University,Zhengzhou,China,450000","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403826","display_name":"Xiaotong Zhang","orcid":"https://orcid.org/0000-0002-9197-1421"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":["Fudan University,Shanghai,China,200000"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China,200000","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058922709","display_name":"Fengzhe Zhang","orcid":"https://orcid.org/0000-0002-7584-1045"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengzhe Zhang","raw_affiliation_strings":["Fudan University,Shanghai,China,200000"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China,200000","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112914699","display_name":"Yijing Song","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijing Song","raw_affiliation_strings":["Fudan University,Shanghai,China,200000"],"affiliations":[{"raw_affiliation_string":"Fudan University,Shanghai,China,200000","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124116038","display_name":"Xiaofeng Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Qi","raw_affiliation_strings":["Information Engineering University,Zhengzhou,China,450000"],"affiliations":[{"raw_affiliation_string":"Information Engineering University,Zhengzhou,China,450000","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056980092","display_name":"Yanzhao Gao","orcid":"https://orcid.org/0009-0000-1987-892X"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanzhao Gao","raw_affiliation_strings":["Information Engineering University,Zhengzhou,China,450000"],"affiliations":[{"raw_affiliation_string":"Information Engineering University,Zhengzhou,China,450000","institution_ids":["https://openalex.org/I169689159"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Zhang","raw_affiliation_strings":["Information Engineering University,Zhengzhou,China,450000"],"affiliations":[{"raw_affiliation_string":"Information Engineering University,Zhengzhou,China,450000","institution_ids":["https://openalex.org/I169689159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5124121709"],"corresponding_institution_ids":["https://openalex.org/I169689159"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71914494,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2792","last_page":"2797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.8557000160217285,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.8557000160217285,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.032600000500679016,"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/T14347","display_name":"Big Data and Digital Economy","score":0.017500000074505806,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5742999911308289},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.551800012588501},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.54830002784729},{"id":"https://openalex.org/keywords/graph-partition","display_name":"Graph partition","score":0.5458999872207642},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5241000056266785},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44839999079704285},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4440999925136566},{"id":"https://openalex.org/keywords/integer-programming","display_name":"Integer programming","score":0.4429999887943268},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42320001125335693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8285999894142151},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5742999911308289},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.54830002784729},{"id":"https://openalex.org/C48903430","wikidata":"https://www.wikidata.org/wiki/Q491370","display_name":"Graph partition","level":3,"score":0.5458999872207642},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5241000056266785},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4453999996185303},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C56086750","wikidata":"https://www.wikidata.org/wiki/Q6042592","display_name":"Integer programming","level":2,"score":0.4429999887943268},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3995000123977661},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3700999915599823},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C127964446","wikidata":"https://www.wikidata.org/wiki/Q1092142","display_name":"Computational resource","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26840001344680786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2608976729","https://openalex.org/W2969388332","https://openalex.org/W3132107458","https://openalex.org/W3204998121","https://openalex.org/W3206832494","https://openalex.org/W3215210342","https://openalex.org/W4206016550","https://openalex.org/W4382119135","https://openalex.org/W4392061646","https://openalex.org/W4392796680","https://openalex.org/W4394010159","https://openalex.org/W4395117922","https://openalex.org/W4399121685","https://openalex.org/W4403277875","https://openalex.org/W4404400671","https://openalex.org/W4408223174","https://openalex.org/W4408590384","https://openalex.org/W4415796899"],"related_works":[],"abstract_inverted_index":{"Expanding":[0],"the":[1,14,19,39,49,117],"scale":[2],"of":[3,18,52,80,162],"deep":[4],"neural":[5],"networks":[6],"(DNNs)":[7],"is":[8,34],"a":[9,30,53,127,159],"fundamental":[10],"approach":[11],"to":[12,26,37,43,62,92,110,136,171,177],"improving":[13],"performance":[15,71],"and":[16,45,69,78,100,119,131,147,168,195],"accuracy":[17],"model.":[20],"However,":[21],"as":[22,126],"DNN":[23,54,163],"models":[24,164],"continue":[25],"grow":[27],"in":[28,85,180],"complexity,":[29],"single":[31],"computing":[32],"accelerator":[33],"often":[35,83],"inadequate":[36],"accommodate":[38],"entire":[40],"model,":[41],"leading":[42],"computational":[44,81],"memory":[46,148],"bottlenecks.":[47],"Distributing":[48],"computation":[50],"graph":[51],"across":[55,95,199],"multiple":[56],"accelerators":[57],"offers":[58],"an":[59,138],"effective":[60],"solution":[61,140],"this":[63,105,124],"challenge,":[64],"enabling":[65],"better":[66],"resource":[67],"utilization":[68],"improved":[70],"scalability.":[72],"Existing":[73],"methods":[74],"for":[75],"coarse-grained":[76],"partitioning":[77,118],"mapping":[79,120],"graph,":[82],"resulting":[84],"suboptimal":[86],"solutions.":[87],"This":[88],"separation":[89],"can":[90],"lead":[91],"imbalanced":[93],"workloads":[94],"accelerators,":[96],"reducing":[97,192],"pipeline":[98],"efficiency":[99],"overall":[101],"system":[102],"performance.":[103],"In":[104],"work,":[106],"we":[107,154],"propose":[108],"OLMP":[109,174,187],"address":[111],"these":[112],"limitations,":[113],"which":[114],"jointly":[115],"optimizes":[116],"processes.":[121],"We":[122],"formulate":[123],"problem":[125],"combinatorial":[128],"optimization":[129],"task":[130],"employ":[132],"Mixed":[133],"Integer":[134],"Programming":[135],"find":[137],"optimal":[139],"that":[141,186],"balances":[142],"execution":[143],"time,":[144],"workload":[145],"distribution,":[146],"constraints.":[149],"To":[150],"validate":[151],"our":[152],"approach,":[153],"conducted":[155],"extensive":[156],"experiments":[157],"on":[158],"diverse":[160],"set":[161],"with":[165],"varying":[166],"scales":[167],"architectures.":[169],"Compared":[170],"existing":[172,189],"approaches,":[173],"achieves":[175],"up":[176],"2.64\u00d7":[178],"speedup":[179],"training":[181,193],"time.":[182],"Experimental":[183],"results":[184],"demonstrate":[185],"outperforms":[188],"methods,":[190],"significantly":[191],"time":[194],"enhancing":[196],"load":[197],"balancing":[198],"accelerators.":[200]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}