{"id":"https://openalex.org/W4401568719","doi":"https://doi.org/10.23919/date58400.2024.10546679","title":"TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Training","display_name":"TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Training","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4401568719","doi":"https://doi.org/10.23919/date58400.2024.10546679"},"language":"en","primary_location":{"id":"doi:10.23919/date58400.2024.10546679","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100429199","display_name":"Dong\u2010Hyun Lee","orcid":"https://orcid.org/0000-0002-2678-2413"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donghyun Lee","raw_affiliation_strings":["Yale University,Department of Electrical Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057610010","display_name":"Ruokai Yin","orcid":"https://orcid.org/0000-0002-7550-0638"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruokai Yin","raw_affiliation_strings":["Yale University,Department of Electrical Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082196231","display_name":"Youngeun Kim","orcid":"https://orcid.org/0000-0002-3542-7720"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngeun Kim","raw_affiliation_strings":["Yale University,Department of Electrical Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050796355","display_name":"Abhishek Moitra","orcid":"https://orcid.org/0000-0002-0534-5206"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Moitra","raw_affiliation_strings":["Yale University,Department of Electrical Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443277","display_name":"Yuhang Li","orcid":"https://orcid.org/0000-0002-9364-4125"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhang Li","raw_affiliation_strings":["Yale University,Department of Electrical Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050310538","display_name":"Priyadarshini Panda","orcid":"https://orcid.org/0000-0002-4167-6782"},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Priyadarshini Panda","raw_affiliation_strings":["Yale University,Department of Electrical Engineering,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University,Department of Electrical Engineering,USA","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32971472"],"apc_list":null,"apc_paid":null,"fwci":2.5559,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.86934673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9656999707221985,"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"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9656999707221985,"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"}},{"id":"https://openalex.org/T13650","display_name":"Computational Physics and Python Applications","score":0.9390000104904175,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9387000203132629,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spiking-neural-network","display_name":"Spiking neural network","score":0.6854140162467957},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6103913187980652},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5995556712150574},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.58888840675354},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5139448046684265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4438605308532715},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"Tensor decomposition","score":0.4156862199306488},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.31129908561706543},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1449146866798401},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06422513723373413},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.046682000160217285}],"concepts":[{"id":"https://openalex.org/C11731999","wikidata":"https://www.wikidata.org/wiki/Q9067355","display_name":"Spiking neural network","level":3,"score":0.6854140162467957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6103913187980652},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5995556712150574},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.58888840675354},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5139448046684265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438605308532715},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.4156862199306488},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.31129908561706543},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1449146866798401},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06422513723373413},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.046682000160217285},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date58400.2024.10546679","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8767942003","display_name":null,"funder_award_id":"2312366,2318152","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W69540849","https://openalex.org/W1645800954","https://openalex.org/W1993482030","https://openalex.org/W2119412403","https://openalex.org/W2164653071","https://openalex.org/W2621826044","https://openalex.org/W2745933219","https://openalex.org/W2783525259","https://openalex.org/W2891530223","https://openalex.org/W2892077605","https://openalex.org/W2962804204","https://openalex.org/W2981609437","https://openalex.org/W2990793844","https://openalex.org/W3042725081","https://openalex.org/W3048230991","https://openalex.org/W3097140984","https://openalex.org/W3102750118","https://openalex.org/W3159830151","https://openalex.org/W3168927686","https://openalex.org/W3186703306","https://openalex.org/W3199910846","https://openalex.org/W4221155907","https://openalex.org/W4221164080","https://openalex.org/W4285188871","https://openalex.org/W4312348535","https://openalex.org/W4382466669","https://openalex.org/W4386071675","https://openalex.org/W4391661519","https://openalex.org/W4396680641","https://openalex.org/W6602850020","https://openalex.org/W6754595668","https://openalex.org/W6809648081"],"related_works":["https://openalex.org/W4379256054","https://openalex.org/W2093953080","https://openalex.org/W2911706637","https://openalex.org/W47805180","https://openalex.org/W3216281372","https://openalex.org/W2963838862","https://openalex.org/W2608089480","https://openalex.org/W3015641590","https://openalex.org/W2987657992","https://openalex.org/W4297666106"],"abstract_inverted_index":{"Spiking":[0,52],"Neural":[1,53],"Networks":[2,54],"(SNNs)":[3],"have":[4],"gained":[5],"significant":[6],"attention":[7],"as":[8,81],"a":[9,56,77,136],"potentially":[10],"energy-efficient":[11],"alternative":[12,83],"for":[13,51,167],"standard":[14],"neural":[15],"networks":[16],"with":[17,171],"their":[18],"sparse":[19],"binary":[20],"activation.":[21],"However,":[22],"SNNs":[23],"suffer":[24],"from":[25],"memory":[26],"and":[27,34,71,126,130,160],"computation":[28,79],"overhead":[29],"due":[30],"to":[31,84,140],"spatio-temporal":[32],"dynamics":[33],"multiple":[35],"backpropagation":[36],"computations":[37],"across":[38],"timesteps":[39],"during":[40,165],"training.":[41],"To":[42,100],"address":[43],"this":[44,106],"issue,":[45],"we":[46,75],"introduce":[47],"Tensor":[48],"Train":[49],"Decomposition":[50],"(TT-SNN),":[55],"method":[57,122],"that":[58],"reduces":[59],"model":[60],"size":[61],"through":[62],"trainable":[63],"weight":[64],"decomposition,":[65],"resulting":[66],"in":[67,117,145,152],"reduced":[68],"storage,":[69],"FLOPs,":[70],"latency.":[72],"In":[73],"addition,":[74],"propose":[76,135],"parallel":[78],"pipeline":[80],"an":[82],"the":[85,101,108,143,168],"typical":[86],"sequential":[87],"tensor":[88,115],"computation,":[89],"which":[90],"can":[91],"be":[92],"flexibly":[93],"integrated":[94],"into":[95],"various":[96],"existing":[97],"SNN":[98],"architectures.":[99],"best":[102],"of":[103,110,114],"our":[104,121],"knowledge,":[105],"is":[107],"first":[109],"its":[111],"kind":[112],"application":[113],"decomposition":[116],"SNNs.":[118],"We":[119,133],"validate":[120],"using":[123],"both":[124],"static":[125],"dynamic":[127],"datasets,":[128],"CIFAR1I0/100":[129],"N-Caltechl0l,":[131],"respectively.":[132],"also":[134],"TT-SNN-tailored":[137],"training":[138,156,161,166],"accelerator":[139],"fully":[141],"harness":[142],"parallelism":[144],"TT-SNN.":[146],"Our":[147],"results":[148],"demonstrate":[149],"substantial":[150],"reductions":[151],"parameter":[153],"size$(7.98\\times)$,":[154],"FLOPs$(9.25\\times)$,":[155],"time":[157],"(17.7":[158],"%),":[159],"energy":[162],"(28.3":[163],"%)":[164],"N-Caltechl0l":[169],"dataset,":[170],"negligible":[172],"accuracy":[173],"degradation.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}