{"id":"https://openalex.org/W7163511286","doi":"https://doi.org/10.23919/date69613.2026.11539743","title":"GCPT: Gradient-aware Clustering Method for Efficient Post-Training Quantization in Large Neural Networks","display_name":"GCPT: Gradient-aware Clustering Method for Efficient Post-Training Quantization in Large Neural Networks","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7163511286","doi":"https://doi.org/10.23919/date69613.2026.11539743"},"language":"en","primary_location":{"id":"doi:10.23919/date69613.2026.11539743","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation & Test in Europe Conference (DATE)","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/A5085508585","display_name":"Chuyi Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chuyi Dai","raw_affiliation_strings":["College of Integrated Circuits & Micro-Nano Electronics School of Integrated Circuits, Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits & Micro-Nano Electronics School of Integrated Circuits, Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137879845","display_name":"Chen Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chen Ye","raw_affiliation_strings":["College of Integrated Circuits & Micro-Nano Electronics School of Integrated Circuits, Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits & Micro-Nano Electronics School of Integrated Circuits, Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455077","display_name":"Zeyu Li","orcid":"https://orcid.org/0009-0008-4381-0544"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zeyu Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Electronics and Computer Engineering Department,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Electronics and Computer Engineering Department,Hong Kong,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137896104","display_name":"Jun Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jun Tao","raw_affiliation_strings":["College of Integrated Circuits & Micro-Nano Electronics School of Integrated Circuits, Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Integrated Circuits & Micro-Nano Electronics School of Integrated Circuits, Fudan University,State Key Laboratory of Integrated Chips and Systems,Shanghai,China","institution_ids":["https://openalex.org/I4210124274"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137884270","display_name":"Wei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Electronics and Computer Engineering Department,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Electronics and Computer Engineering Department,Hong Kong,China","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070194930","display_name":"Grace Li Zhang","orcid":"https://orcid.org/0000-0002-8289-9288"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Grace Li Zhang","raw_affiliation_strings":["TU Darmstadt,Hardware for AI Group,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Darmstadt,Hardware for AI Group,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137858865","display_name":"Xin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Duke Kunshan University,Digital Innovation Research Center,Kunshan,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Digital Innovation Research Center,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"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":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.2596000134944916,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.2596000134944916,"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":0.25780001282691956,"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":0.10369999706745148,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.5342000126838684},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5170000195503235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.3831999897956848},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.3700999915599823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6223000288009644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472000241279602},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5342000126838684},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2856000065803528},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/date69613.2026.11539743","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-172666","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-172666","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2754084392","https://openalex.org/W2946609015","https://openalex.org/W2963122961","https://openalex.org/W2996908057","https://openalex.org/W2998617917","https://openalex.org/W3016597266","https://openalex.org/W3100985894","https://openalex.org/W3137147200","https://openalex.org/W3163465952","https://openalex.org/W4392181806","https://openalex.org/W4402670692"],"related_works":[],"abstract_inverted_index":{"Large-scale":[0],"neural":[1],"network":[2],"models":[3,121],"have":[4],"achieved":[5],"outstanding":[6],"performance":[7],"across":[8],"diverse":[9],"tasks,":[10],"but":[11],"often":[12],"come":[13],"with":[14,90,106],"expensive":[15],"computational":[16,37,132],"costs.":[17],"In":[18],"this":[19],"paper,":[20],"we":[21],"propose":[22],"a":[23,66],"gradient-aware":[24,53],"clustering":[25],"method":[26,127],"for":[27],"post-training":[28],"quantization":[29],"(GCPT)":[30],"in":[31,93],"order":[32],"to":[33,43,55,72,81,130,143],"effectively":[34],"reduce":[35],"the":[36,45,56,74,77,87,94,102,107,112,124],"overhead.":[38],"Our":[39],"key":[40],"idea":[41],"is":[42,104],"cluster":[44,70,96],"weights":[46,62,92],"of":[47,69,76,114],"linear":[48],"layers":[49],"based":[50],"on":[51,118],"their":[52],"contributions":[54],"overall":[57],"loss":[58,78],"function.":[59],"Afterwards,":[60],"all":[61],"are":[63,97],"replaced":[64],"by":[65],"small":[67],"set":[68],"centroids":[71],"minimize":[73],"variation":[75],"function":[79],"due":[80],"quantization.":[82],"To":[83],"further":[84],"accelerate":[85],"inference,":[86],"inputs":[88],"associated":[89],"those":[91],"same":[95],"first":[98],"aggregated":[99],"and":[100,139],"then":[101],"sum":[103],"multiplied":[105],"shared":[108],"centroid,":[109],"thereby":[110],"reducing":[111],"number":[113],"scalar":[115],"multiplications.":[116],"Experiments":[117],"three":[119],"large-scale":[120],"demonstrate":[122],"that":[123],"proposed":[125],"GCPT":[126],"achieves":[128],"up":[129],"93.8%":[131],"cost":[133],"reduction,":[134],"while":[135],"preserving":[136],"memory":[137],"usage":[138],"inference":[140],"accuracy,":[141],"compared":[142],"other":[144],"state-of-the-art":[145],"methods.":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-05T00:00:00"}