{"id":"https://openalex.org/W4406208347","doi":"https://doi.org/10.1109/tpami.2025.3527498","title":"Latent Weight Quantization for Integerized Training of Deep Neural Networks","display_name":"Latent Weight Quantization for Integerized Training of Deep Neural Networks","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4406208347","doi":"https://doi.org/10.1109/tpami.2025.3527498","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030978"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3527498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3527498","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5101631903","display_name":"Wen Fei","orcid":"https://orcid.org/0000-0002-1682-4480"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Fei","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1682-4480","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045342512","display_name":"Wenrui Dai","orcid":"https://orcid.org/0000-0003-2522-5778"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Dai","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2522-5778","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068498390","display_name":"L.L. Zhang","orcid":"https://orcid.org/0000-0002-6788-5857"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Zhang","raw_affiliation_strings":["Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou, China","School of Computer Science and Technology, Donghua University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6788-5857","affiliations":[{"raw_affiliation_string":"Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Computer Science and Technology, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001975771","display_name":"Luoming Zhang","orcid":"https://orcid.org/0000-0003-2188-4485"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luoming Zhang","raw_affiliation_strings":["Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou, China","School of Computer Science and Technology, Donghua University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2188-4485","affiliations":[{"raw_affiliation_string":"Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"School of Computer Science and Technology, Donghua University, Shanghai, China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675587","display_name":"Chenglin Li","orcid":"https://orcid.org/0000-0003-2888-594X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglin Li","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2888-594X","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016006337","display_name":"Junni Zou","orcid":"https://orcid.org/0000-0002-9694-9880"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junni Zou","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9694-9880","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Xiong","raw_affiliation_strings":["Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4552-0029","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66330641,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"47","issue":"4","first_page":"2816","last_page":"2832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9979000091552734,"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":0.9979000091552734,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.996399998664856,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.6613730788230896},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.6500382423400879},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6200135946273804},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5334468483924866},{"id":"https://openalex.org/keywords/linde\u2013buzo\u2013gray-algorithm","display_name":"Linde\u2013Buzo\u2013Gray algorithm","score":0.5261402130126953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46828076243400574},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41460439562797546},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38669446110725403}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6613730788230896},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.6500382423400879},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6200135946273804},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5334468483924866},{"id":"https://openalex.org/C93372532","wikidata":"https://www.wikidata.org/wiki/Q6552455","display_name":"Linde\u2013Buzo\u2013Gray algorithm","level":3,"score":0.5261402130126953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46828076243400574},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41460439562797546},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38669446110725403}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3527498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3527498","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40030978","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030978","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1080903817","display_name":null,"funder_award_id":"62320106003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2048617456","display_name":null,"funder_award_id":"62301299","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2895017225","display_name":null,"funder_award_id":"U24A20251","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3438946646","display_name":null,"funder_award_id":"61932022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G376436071","display_name":null,"funder_award_id":"62401357","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4936292138","display_name":null,"funder_award_id":"T2122024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6094063813","display_name":null,"funder_award_id":"62125109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6263369104","display_name":null,"funder_award_id":"62431017","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6308568386","display_name":null,"funder_award_id":"62401366","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7123918047","display_name":null,"funder_award_id":"62120106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7931220373","display_name":null,"funder_award_id":"62371288","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8700549466","display_name":null,"funder_award_id":"61931023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1980287119","https://openalex.org/W2088912280","https://openalex.org/W2130462033","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2963122961","https://openalex.org/W2963163009","https://openalex.org/W2981849318","https://openalex.org/W2999803881","https://openalex.org/W3035232708","https://openalex.org/W3035718760","https://openalex.org/W3128120039","https://openalex.org/W3129831491","https://openalex.org/W3150698441","https://openalex.org/W3164441165","https://openalex.org/W3165976180","https://openalex.org/W3173374050","https://openalex.org/W3205803342","https://openalex.org/W4210961870","https://openalex.org/W4213450901","https://openalex.org/W4220934237","https://openalex.org/W4297383547","https://openalex.org/W4385245566","https://openalex.org/W4386113256","https://openalex.org/W4390970343","https://openalex.org/W6631190155","https://openalex.org/W6703652217","https://openalex.org/W6726497184","https://openalex.org/W6751528251","https://openalex.org/W6753770798","https://openalex.org/W6759579507","https://openalex.org/W6760069825","https://openalex.org/W6763503671","https://openalex.org/W6766673545","https://openalex.org/W6770425567","https://openalex.org/W6776767859","https://openalex.org/W6778883912","https://openalex.org/W6779813529","https://openalex.org/W6785170623","https://openalex.org/W6785662278","https://openalex.org/W6787953186","https://openalex.org/W6788811087","https://openalex.org/W6789240164","https://openalex.org/W6796581206","https://openalex.org/W6802298259","https://openalex.org/W6810983866","https://openalex.org/W6811340617","https://openalex.org/W6838539104","https://openalex.org/W6845547741","https://openalex.org/W6846164622","https://openalex.org/W6847478871","https://openalex.org/W6850625674","https://openalex.org/W6853048723","https://openalex.org/W6853093965","https://openalex.org/W6853251322","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2096936443","https://openalex.org/W2081863301","https://openalex.org/W2352648934","https://openalex.org/W2365109233","https://openalex.org/W145510127","https://openalex.org/W2374856816","https://openalex.org/W1977098967","https://openalex.org/W2378932494","https://openalex.org/W2352292447","https://openalex.org/W2391875658"],"abstract_inverted_index":{"Existing":[0],"methods":[1],"for":[2,36,52,84,132,150],"integerized":[3,12,39,54,82,143],"training":[4,61,105,144],"speed":[5],"up":[6,177],"deep":[7],"learning":[8],"by":[9],"using":[10,186],"low-bitwidth":[11],"weights,":[13,27],"activations,":[14],"gradients,":[15],"and":[16,81,101,125,156,158,166],"optimizer":[17],"buffers.":[18],"However,":[19],"they":[20],"overlook":[21],"the":[22,38,46,76,117,139,187],"issue":[23],"of":[24],"full-precision":[25,108],"latent":[26,48,79,109,148],"which":[28,56],"consume":[29],"excessive":[30],"memory":[31],"to":[32,60,74,97,115,178],"accumulate":[33],"gradient-based":[34],"updates":[35],"optimizing":[37],"weights.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,170],"propose":[45,90],"first":[47],"weight":[49,80,83,100,120,149],"quantization":[50,58,65,73,86],"schema":[51,141],"general":[53],"training,":[55],"minimizes":[57],"perturbation":[59],"process":[62],"via":[63],"residual":[64,72],"with":[66,93,127,145,176],"optimized":[67,114],"dual":[68,91],"quantizer.":[69],"We":[70,88],"leverage":[71],"eliminate":[75],"correlation":[77],"between":[78],"suppressing":[85],"noise.":[87],"further":[89],"quantizer":[92],"optimal":[94],"nonuniform":[95],"codebook":[96,112],"avoid":[98],"frozen":[99],"ensure":[102],"statistically":[103],"unbiased":[104],"trajectory":[106],"as":[107],"weight.":[110],"The":[111],"is":[113],"minimize":[116],"disturbance":[118],"on":[119,182],"update":[121],"under":[122],"importance":[123],"guidance":[124],"achieved":[126],"a":[128],"three-segment":[129],"polyline":[130],"approximation":[131],"hardware-friendly":[133],"implementation.":[134],"Extensive":[135],"experiments":[136],"show":[137],"that":[138],"proposed":[140,188],"allows":[142],"lowest":[146],"4-bit":[147],"various":[151],"architectures":[152],"including":[153],"ResNets,":[154],"MobileNetV2,":[155],"Transformers,":[157],"yields":[159],"negligible":[160],"performance":[161],"loss":[162],"in":[163],"image":[164],"classification":[165],"text":[167],"generation.":[168],"Furthermore,":[169],"successfully":[171],"fine-tune":[172],"Large":[173],"Language":[174],"Models":[175],"13":[179],"billion":[180],"parameters":[181],"one":[183],"single":[184],"GPU":[185],"schema.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}