{"id":"https://openalex.org/W4312282750","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892626","title":"Ensemble of Tensor Train Decomposition and Quantization Methods for Deep Learning Model Compression","display_name":"Ensemble of Tensor Train Decomposition and Quantization Methods for Deep Learning Model Compression","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312282750","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892626"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892626","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5049599696","display_name":"Olutosin Ajibola Ademola","orcid":"https://orcid.org/0000-0002-4863-5422"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Olutosin Ajibola Ademola","raw_affiliation_strings":["Tallinn University of Technology Embedded AI Research Laboratory,Department of Computer Systems,Tallinn,Estonia,19086"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tallinn University of Technology Embedded AI Research Laboratory,Department of Computer Systems,Tallinn,Estonia,19086","institution_ids":["https://openalex.org/I111112146"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061791014","display_name":"Eduard Petlenkov","orcid":"https://orcid.org/0000-0003-2167-6280"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Petlenkov Eduard","raw_affiliation_strings":["Tallinn University of Technology Centre for Intelligent Systems,Department of Computer Systems,Tallinn,Estonia,19086"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tallinn University of Technology Centre for Intelligent Systems,Department of Computer Systems,Tallinn,Estonia,19086","institution_ids":["https://openalex.org/I111112146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038714483","display_name":"Mairo Leier","orcid":"https://orcid.org/0000-0002-9878-4477"},"institutions":[{"id":"https://openalex.org/I111112146","display_name":"Tallinn University of Technology","ror":"https://ror.org/0443cwa12","country_code":"EE","type":"education","lineage":["https://openalex.org/I111112146"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Leier Mairo","raw_affiliation_strings":["Tallinn University of Technology Embedded AI Research Laboratory,Department of Computer Systems,Tallinn,Estonia,19086"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tallinn University of Technology Embedded AI Research Laboratory,Department of Computer Systems,Tallinn,Estonia,19086","institution_ids":["https://openalex.org/I111112146"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.118,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.43342796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9976000189781189,"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":0.9361000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7986783981323242},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6470046639442444},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6288222074508667},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5939331650733948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5675132274627686},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.44363832473754883},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3718416094779968},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3507840037345886},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3208078145980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986783981323242},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6470046639442444},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6288222074508667},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5939331650733948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5675132274627686},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.44363832473754883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3718416094779968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3507840037345886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3208078145980835}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892626","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G5168270418","display_name":"Intelligent Control Systems for Industry 4.0","funder_award_id":"PRG658","funder_id":"https://openalex.org/F4320321090","funder_display_name":"Eesti Teadusagentuur"}],"funders":[{"id":"https://openalex.org/F4320321090","display_name":"Eesti Teadusagentuur","ror":"https://ror.org/00jjeja18"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1533026269","https://openalex.org/W1902934009","https://openalex.org/W2163605009","https://openalex.org/W2300242332","https://openalex.org/W2766839578","https://openalex.org/W2783318359","https://openalex.org/W2794926691","https://openalex.org/W2905307300","https://openalex.org/W2940612399","https://openalex.org/W2950248853","https://openalex.org/W2962706989","https://openalex.org/W2963674932","https://openalex.org/W2971275988","https://openalex.org/W3008684984","https://openalex.org/W3046175167","https://openalex.org/W3202442802","https://openalex.org/W3212555642","https://openalex.org/W6684191040","https://openalex.org/W6684563725","https://openalex.org/W6747544394","https://openalex.org/W6891812158"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4375867731","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W4380075502"],"abstract_inverted_index":{"We":[0,169,183,213],"have":[1,107,200],"seen":[2],"tremendous":[3],"growth":[4,30],"in":[5,16,83,110,188],"the":[6,14,35,61,67,90,123,149,154,161,171,174,181],"adoption":[7],"of":[8,64,74,92,131,153,173],"convolutional":[9],"neural":[10,51],"networks":[11,52],"(CNNs)":[12],"over":[13,39],"years":[15],"solving":[17],"real-world":[18],"problems":[19],"such":[20],"as":[21],"image":[22],"analysis,":[23],"object":[24],"detection,":[25],"auto-translation,":[26],"etc.":[27],"This":[28],"exponential":[29],"has":[31],"been":[32,108,201],"due":[33,88],"to":[34,69,89,120,147,160],"unprecedented":[36],"outcomes":[37],"achieved":[38,184,202],"traditional":[40],"methods.":[41],"However,":[42],"these":[43],"remarkable":[44],"achievements":[45],"come":[46],"at":[47],"a":[48,185],"cost.":[49],"Convolutional":[50],"are":[53],"memory":[54],"intensive,":[55],"computationally":[56],"expensive,":[57],"and":[58,85,140,151,176,194],"usually":[59],"cause":[60],"underlying":[62],"pieces":[63],"hardware":[65,94],"running":[66],"models":[68,106],"consume":[70],"an":[71,118,129,216],"excessive":[72],"amount":[73],"power":[75],"during":[76],"inference.":[77],"These":[78],"factors":[79,197],"impede":[80],"its":[81],"deployment":[82],"mobile":[84],"embedded":[86],"applications":[87],"availability":[91],"limited":[93],"resources.":[95],"To":[96],"address":[97],"this":[98,114],"problem,":[99],"different":[100,111],"methods":[101,135,211],"for":[102,220],"compressing":[103],"deep":[104],"learning":[105],"presented":[109],"works.":[112],"In":[113],"paper,":[115],"we":[116],"propose":[117],"approach":[119,127],"further":[121,214],"improve":[122],"compression":[124,134,196],"results.":[125],"Our":[126,144],"leverages":[128],"ensemble":[130,155],"two":[132],"model":[133,164,178,189,224],"-":[136],"tensor":[137,208],"train":[138,209],"decomposition":[139,210],"8-bit":[141],"integer":[142],"quantization.":[143],"goal":[145],"is":[146],"demonstrate":[148],"efficiency":[150],"effectiveness":[152],"technique":[156],"by":[157,180],"applying":[158],"it":[159],"baseline":[162,175],"CNN":[163,223],"trained":[165],"on":[166,226],"our":[167,227],"dataset.":[168],"compared":[170,191],"performance":[172],"compressed":[177],"produced":[179],"ensemble.":[182],"57x":[186],"reduction":[187],"size":[190],"with":[192,203],"4x":[193],"17x":[195],"that":[198],"would":[199],"either":[204],"only":[205],"quantization":[206],"or":[207],"respectively.":[212],"demonstrated":[215],"end-to-end":[217],"trainable":[218],"pipeline":[219],"training":[221],"any":[222],"based":[225],"proposed":[228],"method.":[229]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}