{"id":"https://openalex.org/W2919207648","doi":"https://doi.org/10.48550/arxiv.1901.10787","title":"Tensorized Embedding Layers for Efficient Model Compression","display_name":"Tensorized Embedding Layers for Efficient Model Compression","publication_year":2019,"publication_date":"2019-01-30","ids":{"openalex":"https://openalex.org/W2919207648","doi":"https://doi.org/10.48550/arxiv.1901.10787","mag":"2919207648"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1901.10787","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.10787","pdf_url":"https://arxiv.org/pdf/1901.10787","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.10787","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088392468","display_name":"Oleksii Hrinchuk","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hrinchuk, Oleksii","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040956144","display_name":"Valentin Khrulkov","orcid":"https://orcid.org/0009-0000-6694-5398","observed_orcids":["https://orcid.org/0009-0000-6694-5398"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khrulkov, Valentin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013359809","display_name":"Leyla Mirvakhabova","orcid":"https://orcid.org/0009-0000-5798-8492","observed_orcids":["https://orcid.org/0009-0000-5798-8492"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirvakhabova, Leyla","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Orlova, Elena","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Orlova, Elena","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004111307","display_name":"Ivan Valer'evich Oseledets","orcid":"https://orcid.org/0000-0003-2071-2163","observed_orcids":["https://orcid.org/0000-0003-2071-2163"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oseledets, Ivan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.48510000109672546,"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":0.48510000109672546,"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/T10028","display_name":"Topic Modeling","score":0.4284999966621399,"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":0.016100000590085983,"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/embedding-layer","display_name":"embedding layer","score":0.8119999766349792},{"id":"https://openalex.org/keywords/tensor-train-decomposition","display_name":"tensor train decomposition","score":0.8410000205039978},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.9559999704360962},{"id":"https://openalex.org/keywords/large-vocabulary","display_name":"large vocabulary","score":0.5770000219345093},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"natural language processing","score":0.6200000047683716},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.6859999895095825},{"id":"https://openalex.org/keywords/lstm","display_name":"LSTM","score":0.8759999871253967},{"id":"https://openalex.org/keywords/mlp","display_name":"MLP","score":0.6890000104904175}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7762239575386047},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.6352900266647339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4371691942214966},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.24456080794334412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15598005056381226},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.10577750205993652}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1901.10787","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.10787","pdf_url":"https://arxiv.org/pdf/1901.10787","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1901.10787","doi":"https://doi.org/10.48550/arxiv.1901.10787","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1901.10787","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.10787","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.10787","pdf_url":"https://arxiv.org/pdf/1901.10787","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.550000011920929,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1751050961","https://openalex.org/W1826234144","https://openalex.org/W1967077133","https://openalex.org/W1993482030","https://openalex.org/W2000215628","https://openalex.org/W2014237348","https://openalex.org/W2025267249","https://openalex.org/W2058641082","https://openalex.org/W2064675550","https://openalex.org/W2076618162","https://openalex.org/W2113459411","https://openalex.org/W2121739212","https://openalex.org/W2121879602","https://openalex.org/W2130942839","https://openalex.org/W2157331557","https://openalex.org/W2177847924","https://openalex.org/W2251939518","https://openalex.org/W2294543795","https://openalex.org/W2431890537","https://openalex.org/W2460130460","https://openalex.org/W2514713644","https://openalex.org/W2524428287","https://openalex.org/W2525332836","https://openalex.org/W2525778437","https://openalex.org/W2549416390","https://openalex.org/W2559813832","https://openalex.org/W2563351168","https://openalex.org/W2574872930","https://openalex.org/W2612445135","https://openalex.org/W2619959423","https://openalex.org/W2626778328","https://openalex.org/W2733236492","https://openalex.org/W2739963392","https://openalex.org/W2754084392","https://openalex.org/W2765932895","https://openalex.org/W2767321762","https://openalex.org/W2767768936","https://openalex.org/W2788717888","https://openalex.org/W2789142637","https://openalex.org/W2794137799","https://openalex.org/W2809532345","https://openalex.org/W2894175714","https://openalex.org/W2899771611","https://openalex.org/W2901362701","https://openalex.org/W2908336025","https://openalex.org/W2911109671","https://openalex.org/W2917889548","https://openalex.org/W2950967261","https://openalex.org/W2952689122","https://openalex.org/W2962766718","https://openalex.org/W2962784628","https://openalex.org/W2963036352","https://openalex.org/W2963048316","https://openalex.org/W2963341956","https://openalex.org/W2963674932","https://openalex.org/W2964299589","https://openalex.org/W2964308564","https://openalex.org/W2969855422","https://openalex.org/W2970213198","https://openalex.org/W2970971581","https://openalex.org/W2975059944"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857"],"abstract_inverted_index":{"The":[0],"embedding":[1,51],"layers":[2,52],"transforming":[3],"input":[4],"words":[5],"into":[6],"real":[7],"vectors":[8],"are":[9],"the":[10,24,28,55,63,67,96],"key":[11],"components":[12],"of":[13,49,69,88,107],"deep":[14],"neural":[15],"networks":[16],"used":[17],"in":[18,39,78,90],"natural":[19,91],"language":[20,92],"processing.":[21],"However,":[22],"when":[23],"vocabulary":[25],"is":[26],"large,":[27],"corresponding":[29],"weight":[30],"matrices":[31],"can":[32],"be":[33],"enormous,":[34],"which":[35,60],"precludes":[36],"their":[37],"deployment":[38],"a":[40,46,70,75,85,104],"limited":[41],"resource":[42],"setting.":[43],"We":[44,80],"introduce":[45],"novel":[47],"way":[48],"parametrizing":[50],"based":[53],"on":[54,84],"Tensor":[56],"Train":[57],"(TT)":[58],"decomposition,":[59],"allows":[61],"compressing":[62],"model":[64],"significantly":[65],"at":[66],"cost":[68],"negligible":[71],"drop":[72],"or":[73],"even":[74],"slight":[76],"gain":[77],"performance.":[79],"evaluate":[81],"our":[82],"method":[83],"wide":[86,105],"range":[87,106],"benchmarks":[89],"processing":[93],"and":[94,100,113],"analyze":[95],"trade-off":[97],"between":[98],"performance":[99],"compression":[101],"ratios":[102],"for":[103],"architectures,":[108],"from":[109],"MLPs":[110],"to":[111],"LSTMs":[112],"Transformers.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2019-03-11T00:00:00"}