{"id":"https://openalex.org/W4403584939","doi":"https://doi.org/10.1145/3701033","title":"STCO: Enhancing Training Efficiency via Structured Sparse Tensor Compilation Optimization","display_name":"STCO: Enhancing Training Efficiency via Structured Sparse Tensor Compilation Optimization","publication_year":2024,"publication_date":"2024-10-21","ids":{"openalex":"https://openalex.org/W4403584939","doi":"https://doi.org/10.1145/3701033"},"language":"en","primary_location":{"id":"doi:10.1145/3701033","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701033","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701033","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701033","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102989014","display_name":"Shiyuan Huang","orcid":"https://orcid.org/0000-0002-8086-6802"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shiyuan Huang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Shanghai Qi Zhi Institute, Shanghai China","Shanghai Qi Zhi Institute, Shanghai China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Shanghai Qi Zhi Institute, Shanghai China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017670541","display_name":"Fangxin Liu","orcid":"https://orcid.org/0000-0002-8769-293X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"fangxin liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai China and Shanghai Qi Zhi Institute, Shanghai China","Shanghai Qi Zhi Institute, Shanghai China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai China and Shanghai Qi Zhi Institute, Shanghai China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107864957","display_name":"Tian Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Li","raw_affiliation_strings":["Huawei Technologies Co Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107269495","display_name":"Zongwu Wang","orcid":"https://orcid.org/0009-0003-2157-4927"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongwu Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai China and Shanghai Qi Zhi Institute, Shanghai China","Shanghai Qi Zhi Institute, Shanghai China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai China and Shanghai Qi Zhi Institute, Shanghai China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030493839","display_name":"Ning Yang","orcid":"https://orcid.org/0009-0004-6964-8910"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101399528","display_name":"Haoming Li","orcid":"https://orcid.org/0000-0002-2939-6534"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haomin Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053801300","display_name":"Li Jiang","orcid":"https://orcid.org/0000-0002-7353-8798"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai China and Shanghai Qi Zhi Institute, Shanghai China","Shanghai Qi Zhi Institute, Shanghai China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai China and Shanghai Qi Zhi Institute, Shanghai China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai China","institution_ids":["https://openalex.org/I4210122302"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102989014"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210122302"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17932629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":"1","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9878000020980835,"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":0.9878000020980835,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9674999713897705,"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":0.8951924443244934},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5849814414978027},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.507593035697937},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42571738362312317},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33699339628219604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8951924443244934},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5849814414978027},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.507593035697937},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42571738362312317},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33699339628219604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3701033","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701033","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701033","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3701033","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701033","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701033","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5952030521","display_name":null,"funder_award_id":"62402311","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4403584939.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2014807599","https://openalex.org/W2077143534","https://openalex.org/W2095705004","https://openalex.org/W2126004407","https://openalex.org/W2245094585","https://openalex.org/W2322411027","https://openalex.org/W2559655401","https://openalex.org/W2568772110","https://openalex.org/W2590246587","https://openalex.org/W2701971652","https://openalex.org/W2883603666","https://openalex.org/W2914631005","https://openalex.org/W2946529874","https://openalex.org/W3139203094","https://openalex.org/W3151489216","https://openalex.org/W3177452048","https://openalex.org/W4242726609","https://openalex.org/W4255450819","https://openalex.org/W4307380766","https://openalex.org/W4327911434","https://openalex.org/W4383753658","https://openalex.org/W4391986945","https://openalex.org/W4396817063","https://openalex.org/W4403407616"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"Network":[0,11],"sparsification":[1,16],"serves":[2],"as":[3],"an":[4,230],"effective":[5],"technique":[6,79],"to":[7,31,91,144,168,196,213,220,260,296],"accelerate":[8],"Deep":[9],"Neural":[10],"(DNN)":[12],"inference.":[13],"However,":[14],"existing":[15,221],"techniques":[17],"often":[18],"rely":[19],"on":[20,300],"structured":[21,86,103,238,278],"sparsity,":[22],"which":[23,100,128],"yields":[24],"limited":[25],"benefits.":[26],"This":[27,138,202,241],"is":[28,93],"primarily":[29],"due":[30],"the":[32,59,63,94,122,130,134,141,146,165,175,182,191,206,310],"significant":[33,218],"memory":[34],"and":[35,47,110,154,199,292,304,312],"computational":[36,135,248],"overhead":[37,249],"introduced":[38],"by":[39,106],"numerous":[40],"sparse":[41,87,104,156,178,194,214,239,251,279,298],"storage":[42,112],"formats":[43,299],"during":[44,250],"address":[45],"generation":[46],"gradient":[48],"updates.":[49],"Additionally,":[50],"many":[51],"of":[52,148,177,193,256,288,314],"these":[53],"solutions":[54],"are":[55],"tailored":[56,236],"solely":[57],"for":[58,237,273,322],"inference":[60,162,324],"phase,":[61],"neglecting":[62],"crucial":[64],"training":[65,83,207,226,275],"phase.":[66],"In":[67],"this":[68],"article,":[69],"we":[70,228],"introduce":[71],"STCO,":[72],"a":[73,118,160,210,270],"novel":[74],"Sparse":[75],"Tensor":[76],"Compilation":[77],"Optimization":[78],"that":[80,283],"significantly":[81],"enhances":[82],"efficiency":[84,147,276,311],"through":[85],"tensor":[88,149,157,171,179,215,252],"compilation.":[89],"Central":[90],"STCO":[92,257,284],"Tensorization-aware":[95],"Index":[96],"Entity":[97],"(TIE)":[98],"format,":[99],"effectively":[101],"represents":[102],"tensors":[105],"eliminating":[107],"redundant":[108],"indices":[109],"minimizing":[111],"overhead.":[113],"The":[114,254],"TIE":[115,142,184],"format":[116,143],"plays":[117],"pivotal":[119],"role":[120],"in":[121,318],"Address-carry":[123],"flow":[124,167,233],"(AC":[125],"flow)":[126],"pass,":[127],"optimizes":[129],"data":[131],"layout":[132],"at":[133],"graph":[136],"level.":[137],"pass":[139,163,235,242],"leverages":[140],"enhance":[145],"representations,":[150],"enabling":[151],"more":[152],"compact":[153],"efficient":[155,244],"storage.":[158],"Meanwhile,":[159],"shape":[161],"utilizes":[164],"AC":[166,232],"derive":[169],"optimized":[170],"shapes,":[172],"further":[173,224],"refining":[174],"performance":[176],"operations.":[180,253],"Moreover,":[181],"Address-Carry":[183],"Flow":[185],"dynamically":[186],"tracks":[187],"nonzero":[188],"addresses,":[189,245],"extending":[190],"benefits":[192],"optimization":[195,234],"both":[197],"forward":[198],"backward":[200],"propagation.":[201],"seamless":[203],"integration":[204],"into":[205,264],"pipeline":[208],"enables":[209],"smooth":[211],"transition":[212],"compilation":[216],"without":[217],"modifications":[219],"codebases.":[222],"To":[223],"boost":[225],"performance,":[227],"implement":[229],"operator-level":[231],"tensors.":[240,280],"generates":[243],"ensuring":[246],"minimal":[247],"flexibility":[255],"allows":[258],"it":[259],"be":[261],"efficiently":[262],"integrated":[263],"various":[265],"frameworks":[266],"or":[267],"compilers,":[268],"providing":[269],"robust":[271],"solution":[272],"enhancing":[274],"with":[277],"Experiments":[281],"demonstrated":[282],"achieved":[285],"impressive":[286],"speedups":[287],"3.64\u00d7,":[289],"5.43\u00d7,":[290],"4.89\u00d7,":[291],"3.91\u00d7":[293],"when":[294],"compared":[295],"state-of-the-art":[297],"VGG16,":[301],"ResNet-18,":[302],"MobileNetV1,":[303],"MobileNetV2,":[305],"respectively.":[306],"These":[307],"findings":[308],"underscore":[309],"superiority":[313],"our":[315],"proposed":[316],"approach":[317],"leveraging":[319],"unstructured":[320],"sparsity":[321],"DNN":[323],"acceleration.":[325]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}