{"id":"https://openalex.org/W7161799668","doi":"https://doi.org/10.48550/arxiv.2605.19842","title":"Fast Tensorization of Neural Networks via Slice-wise Feature Distillation","display_name":"Fast Tensorization of Neural Networks via Slice-wise Feature Distillation","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161799668","doi":"https://doi.org/10.48550/arxiv.2605.19842"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.19842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010993400","display_name":"Safa Hamreras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamreras, Safa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087485642","display_name":"Sukhbinder Singh","orcid":"https://orcid.org/0000-0002-3099-4179"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Sukhbinder","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020314133","display_name":"Rom\u00e1n Or\u00fas","orcid":"https://orcid.org/0000-0002-4496-8115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Or\u00fas, Rom\u00e1n","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":0,"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/T12303","display_name":"Tensor decomposition and applications","score":0.41119998693466187,"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":0.41119998693466187,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.12150000035762787,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.1152999997138977,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.649399995803833},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5647000074386597},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5580999851226807},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5562999844551086},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5353000164031982},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5163999795913696},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.47540000081062317},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"Tensor decomposition","score":0.4535999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404000163078308},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.649399995803833},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5647000074386597},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5562999844551086},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47450000047683716},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.4535999894142151},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4115000069141388},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C94835093","wikidata":"https://www.wikidata.org/wiki/Q3113333","display_name":"Data compression ratio","level":5,"score":0.34049999713897705},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.2678999900817871},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"doi:10.48550/arxiv.2605.19842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"scalable":[3],"tensorization":[4],"framework":[5],"for":[6],"neural":[7],"network":[8,30],"compression":[9,92,95],"based":[10],"on":[11,22,81,101],"slice-wise":[12],"feature":[13],"distillation.":[14],"Unlike":[15],"conventional":[16,87],"tensor":[17],"decomposition":[18],"methods":[19],"that":[20],"rely":[21],"costly":[23],"global":[24,88],"finetuning,":[25],"our":[26],"approach":[27],"decomposes":[28],"the":[29,58,62,106,109],"into":[31],"slices":[32],"consisting":[33],"of":[34,48,61,108],"either":[35],"individual":[36],"layers":[37,42],"or":[38,43,45],"blocks":[39],"(e.g.,":[40],"convolutional":[41],"MLPs),":[44],"small":[46],"groups":[47],"consecutive":[49],"layers,":[50],"and":[51,75,111],"tensorizes":[52],"each":[53],"slice":[54],"independently":[55],"to":[56,114],"reproduce":[57],"intermediate":[59],"representations":[60],"original":[63],"pretrained":[64],"model.":[65],"This":[66],"modular":[67],"strategy":[68],"improves":[69],"accuracy":[70],"recovery,":[71],"reduces":[72],"data":[73],"requirements,":[74],"enables":[76],"efficient":[77],"parallel":[78],"optimization.":[79,99],"Experiments":[80],"ResNet-34":[82],"show":[83],"significant":[84],"gains":[85],"over":[86],"tensorization,":[89],"achieving":[90],"near-lossless":[91],"at":[93],"moderate":[94],"rates":[96],"with":[97],"faster":[98],"Results":[100],"GPT-2":[102],"XL":[103],"further":[104],"demonstrate":[105],"scalability":[107],"method":[110],"its":[112],"applicability":[113],"large-scale":[115],"models,":[116],"particularly":[117],"in":[118],"distributed":[119],"settings.":[120]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}