{"id":"https://openalex.org/W3015509582","doi":"https://doi.org/10.1109/icassp40776.2020.9053292","title":"A Novel Rank Selection Scheme in Tensor Ring Decomposition Based on Reinforcement Learning for Deep Neural Networks","display_name":"A Novel Rank Selection Scheme in Tensor Ring Decomposition Based on Reinforcement Learning for Deep Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015509582","doi":"https://doi.org/10.1109/icassp40776.2020.9053292","mag":"3015509582"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072368581","display_name":"Zhiyu Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyu Cheng","raw_affiliation_strings":["Baidu Research (US), Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research (US), Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087869694","display_name":"Baopu Li","orcid":"https://orcid.org/0000-0002-9032-3991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baopu Li","raw_affiliation_strings":["Baidu Research (US), Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research (US), Sunnyvale, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083208039","display_name":"Yanwen Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwen Fan","raw_affiliation_strings":["Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041114937","display_name":"Yingze Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingze Bao","raw_affiliation_strings":["Baidu Research (US), Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Research (US), Sunnyvale, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3292","last_page":"3296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9322999715805054,"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"}},{"id":"https://openalex.org/T10305","display_name":"Power System Optimization and Stability","score":0.9128999710083008,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7119162082672119},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.6352502703666687},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.580001950263977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5758719444274902},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.569473922252655},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5494012236595154},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4779201149940491},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4462067186832428},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.42241576313972473},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.41071265935897827},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3435176610946655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19006970524787903}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7119162082672119},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.6352502703666687},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.580001950263977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5758719444274902},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.569473922252655},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5494012236595154},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4779201149940491},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4462067186832428},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.42241576313972473},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.41071265935897827},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3435176610946655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19006970524787903},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053292","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053292","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":47,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1798945469","https://openalex.org/W1963826206","https://openalex.org/W1993482030","https://openalex.org/W2024165284","https://openalex.org/W2119144962","https://openalex.org/W2131524184","https://openalex.org/W2134797427","https://openalex.org/W2156737235","https://openalex.org/W2167215970","https://openalex.org/W2173248099","https://openalex.org/W2431890537","https://openalex.org/W2469230926","https://openalex.org/W2516041031","https://openalex.org/W2559813832","https://openalex.org/W2617994470","https://openalex.org/W2886851211","https://openalex.org/W2906905608","https://openalex.org/W2946049129","https://openalex.org/W2946151451","https://openalex.org/W2949941638","https://openalex.org/W2950248853","https://openalex.org/W2962766718","https://openalex.org/W2962988160","https://openalex.org/W2963048316","https://openalex.org/W2963864421","https://openalex.org/W2964299589","https://openalex.org/W3007602670","https://openalex.org/W3101570982","https://openalex.org/W4297781745","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6638060716","https://openalex.org/W6677580257","https://openalex.org/W6679667936","https://openalex.org/W6679909955","https://openalex.org/W6683195989","https://openalex.org/W6684563725","https://openalex.org/W6684921986","https://openalex.org/W6685627644","https://openalex.org/W6717575008","https://openalex.org/W6730093588","https://openalex.org/W6748780714","https://openalex.org/W6753490951","https://openalex.org/W6762294372","https://openalex.org/W6762761081","https://openalex.org/W6966580395"],"related_works":["https://openalex.org/W2950186459","https://openalex.org/W2170114491","https://openalex.org/W2897298721","https://openalex.org/W2242624680","https://openalex.org/W2136127937","https://openalex.org/W4290987221","https://openalex.org/W2216309014","https://openalex.org/W2569661359","https://openalex.org/W3199841771","https://openalex.org/W4286971555"],"abstract_inverted_index":{"Tensor":[0],"decomposition":[1,20,70,104,149],"has":[2],"been":[3],"proved":[4],"to":[5,39,48,75,119,140],"be":[6],"effective":[7],"for":[8,24,175],"solving":[9],"many":[10,30],"problems":[11],"in":[12,52,86,105,144,150],"signal":[13],"processing":[14],"and":[15,45],"machine":[16],"learning[1].":[17],"Recently,":[18],"tensor":[19,69,94,99,103,147],"finds":[21],"its":[22],"advantage":[23],"compressing":[25,106,180],"deep":[26,33,58,107,181],"neural":[27,34,59,108,182],"networks.":[28],"In":[29],"applications":[31],"of":[32,43,54,62,172,178],"networks,":[35],"it":[36],"is":[37,71,79,135],"critical":[38],"reduce":[40],"the":[41,55,83,111,121,176],"number":[42,171],"parameters":[44],"computation":[46],"workload":[47],"accelerate":[49],"inference":[50],"speed":[51],"deployment":[53],"network.":[56],"Modern":[57],"network":[60],"consists":[61],"multiple":[63],"layers":[64,88,91],"with":[65,92],"multi-array":[66],"weights":[67],"where":[68],"a":[72,129,170],"natural":[73],"way":[74],"perform":[76],"compression.":[77],"It":[78],"achieved":[80],"by":[81,137],"decomposing":[82],"weight":[84],"tensors":[85],"convolutional":[87,152],"or":[89],"fully-connected":[90],"specified":[93],"ranks":[95,112,143],"(e.g.":[96],"canonical":[97],"ranks,":[98],"train":[100],"ranks).":[101],"Conventional":[102],"networks":[109,183],"selects":[110],"manually":[113],"that":[114,157],"requires":[115],"tedious":[116],"human":[117],"efforts":[118],"finetune":[120],"performance.":[122],"To":[123],"overcome":[124],"this":[125],"issue,":[126],"we":[127],"propose":[128],"novel":[130],"rank":[131,161,166],"selection":[132,162,167],"scheme,":[133],"which":[134],"inspired":[136],"reinforcement":[138],"learning,":[139],"automatically":[141],"select":[142],"recently":[145],"studied":[146],"ring":[148],"each":[151],"layer.":[153],"Experimental":[154],"results":[155],"validate":[156],"our":[158],"learning":[159],"based":[160],"significantly":[163],"outperforms":[164],"hand-crafted":[165],"heuristics":[168],"on":[169],"benchmark":[173],"datasets,":[174],"purpose":[177],"effectively":[179],"while":[184],"maintaining":[185],"comparable":[186],"accuracy.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}