{"id":"https://openalex.org/W3090325430","doi":"https://doi.org/10.1109/iscas45731.2020.9181239","title":"Learning Low-Rank Structured Sparsity in Recurrent Neural Networks","display_name":"Learning Low-Rank Structured Sparsity in Recurrent Neural Networks","publication_year":2020,"publication_date":"2020-09-29","ids":{"openalex":"https://openalex.org/W3090325430","doi":"https://doi.org/10.1109/iscas45731.2020.9181239","mag":"3090325430"},"language":"en","primary_location":{"id":"doi:10.1109/iscas45731.2020.9181239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas45731.2020.9181239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5101070527","display_name":"Weijing Wen","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":"Weijing Wen","raw_affiliation_strings":["State Key Lab of ASIC & System, School of Microelectronics, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of ASIC & System, School of Microelectronics, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045825296","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-3523-1138"},"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 Yang","raw_affiliation_strings":["State Key Lab of ASIC & System, School of Microelectronics, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of ASIC & System, School of Microelectronics, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101680116","display_name":"Yangfeng Su","orcid":"https://orcid.org/0000-0002-8744-1591"},"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":"Yangfeng Su","raw_affiliation_strings":["School of Mathematical Sciences, Fudan University, China","School of Mathematical Sciences, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Sciences, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"School of Mathematical Sciences, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054960059","display_name":"Dian Zhou","orcid":"https://orcid.org/0000-0002-2648-5232"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dian Zhou","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064213921","display_name":"Xuan Zeng","orcid":"https://orcid.org/0000-0002-8097-4053"},"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":"Xuan Zeng","raw_affiliation_strings":["State Key Lab of ASIC & System, School of Microelectronics, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of ASIC & System, School of Microelectronics, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9948999881744385,"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/T10320","display_name":"Neural Networks and Applications","score":0.994700014591217,"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/perplexity","display_name":"Perplexity","score":0.8251485824584961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7730976343154907},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7099819183349609},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.5890853404998779},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5795061588287354},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5406432151794434},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.5171924829483032},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5052853226661682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49527707695961},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4901450574398041},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4890938401222229},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.44630804657936096},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3574409484863281},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08655619621276855}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8251485824584961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730976343154907},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7099819183349609},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.5890853404998779},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5795061588287354},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5406432151794434},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.5171924829483032},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5052853226661682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49527707695961},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4901450574398041},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4890938401222229},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.44630804657936096},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3574409484863281},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08655619621276855},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"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:10.1109/iscas45731.2020.9181239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas45731.2020.9181239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1504194272","https://openalex.org/W1591801644","https://openalex.org/W1632114991","https://openalex.org/W1667652561","https://openalex.org/W1845051632","https://openalex.org/W1978259121","https://openalex.org/W1996901117","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2119144962","https://openalex.org/W2138019504","https://openalex.org/W2157331557","https://openalex.org/W2754526845","https://openalex.org/W2950967261","https://openalex.org/W2963000224","https://openalex.org/W2963674932","https://openalex.org/W2963983719","https://openalex.org/W2963991999","https://openalex.org/W2964299589","https://openalex.org/W4294555862","https://openalex.org/W4302296459","https://openalex.org/W6607333740","https://openalex.org/W6635446068","https://openalex.org/W6637151318","https://openalex.org/W6638632666","https://openalex.org/W6674330103","https://openalex.org/W6677580257","https://openalex.org/W6720905350","https://openalex.org/W6725543821","https://openalex.org/W6744208968"],"related_works":["https://openalex.org/W4301800915","https://openalex.org/W2739034105","https://openalex.org/W2963839582","https://openalex.org/W4299838440","https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W2551914602","https://openalex.org/W2964047924","https://openalex.org/W2743945814","https://openalex.org/W2962832505"],"abstract_inverted_index":{"Acceleration":[0],"and":[1,16,23,79,155],"wide":[2],"deployability":[3],"in":[4,50,54],"deeper":[5],"recurrent":[6,42,55,126],"neural":[7,43,56,127,147],"network":[8,128,148],"is":[9,76,140],"hindered":[10],"by":[11,130],"high":[12],"demand":[13],"for":[14,40],"computation":[15],"memory":[17,22],"storage":[18],"on":[19,109,144],"devices":[20],"with":[21,84,133,150],"latency":[24],"constraints.":[25],"In":[26],"this":[27],"work,":[28],"we":[29],"propose":[30],"a":[31],"novel":[32],"regularization":[33,70],"method":[34,75],"to":[35],"learn":[36,81],"hardware-friendly":[37],"sparse":[38,60],"structures":[39],"deep":[41],"networks.":[44],"Considering":[45],"the":[46,63,69,90,105,122],"consistency":[47],"of":[48,62,87,112,124],"dimension":[49,72],"continuous":[51],"time":[52],"units":[53],"networks,":[57],"low-rank":[58],"structured":[59,92,97],"approximations":[61],"weight":[64],"matrices":[65],"are":[66],"learned":[67],"through":[68],"without":[71],"distortion.":[73],"Our":[74],"architecture":[77],"agnostic":[78],"can":[80,120],"compact":[82],"models":[83],"higher":[85],"degree":[86],"sparsity":[88,93,98,102],"than":[89,100,135],"state-of-the-art":[91],"learning":[94],"method.":[95],"The":[96],"rather":[99],"random":[101],"also":[103,141],"facilitates":[104],"hardware":[106],"implementation.":[107],"Experiments":[108],"language":[110],"modeling":[111],"Penn":[113],"TreeBank":[114],"dataset":[115,152],"show":[116],"that":[117],"our":[118],"approach":[119],"reduce":[121],"parameters":[123],"stacked":[125],"model":[129,149],"over":[131],"90%":[132],"less":[134],"1%":[136],"perplexity":[137],"loss.":[138],"It":[139],"successfully":[142],"evaluated":[143],"larger":[145],"highway":[146],"word2vec":[151],"like":[153],"enwik8":[154],"text8":[156],"using":[157],"only":[158],"20M":[159],"weights.":[160]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}