{"id":"https://openalex.org/W4400811325","doi":"https://doi.org/10.1109/aicas59952.2024.10595902","title":"A Novel Number Representation and Its Hardware Support for Accurate Low-Bit Quantization on Large Recommender Systems","display_name":"A Novel Number Representation and Its Hardware Support for Accurate Low-Bit Quantization on Large Recommender Systems","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4400811325","doi":"https://doi.org/10.1109/aicas59952.2024.10595902"},"language":"en","primary_location":{"id":"doi:10.1109/aicas59952.2024.10595902","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aicas59952.2024.10595902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS)","raw_type":"proceedings-article"},"type":"article","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/A5106726112","display_name":"Yu-Da Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu-Da Chu","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electronics,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electronics,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036029066","display_name":"Pei-Hsuan Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pei-Hsuan Kuo","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electronics,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electronics,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108327109","display_name":"Lyu-Ming Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lyu-Ming Ho","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electronics,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electronics,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107969989","display_name":"Juinn-Dar Huang","orcid":"https://orcid.org/0000-0001-5961-7863"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Juinn-Dar Huang","raw_affiliation_strings":["National Yang Ming Chiao Tung University,Institute of Electronics,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Yang Ming Chiao Tung University,Institute of Electronics,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5106726112"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10410802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"437","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9775999784469604,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9775999784469604,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9628999829292297,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9509999752044678,"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":0.777753472328186},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.6872244477272034},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6572263240814209},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5294817686080933},{"id":"https://openalex.org/keywords/bit","display_name":"Bit (key)","score":0.5184780955314636},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.42878246307373047},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3826964497566223},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3736238181591034},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3381812870502472},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2153869867324829},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.17184630036354065},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09100034832954407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777753472328186},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6872244477272034},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6572263240814209},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5294817686080933},{"id":"https://openalex.org/C117011727","wikidata":"https://www.wikidata.org/wiki/Q1278488","display_name":"Bit (key)","level":2,"score":0.5184780955314636},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42878246307373047},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3826964497566223},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3736238181591034},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3381812870502472},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2153869867324829},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.17184630036354065},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09100034832954407},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aicas59952.2024.10595902","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aicas59952.2024.10595902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 6th International Conference on AI Circuits and Systems (AICAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2242818861","https://openalex.org/W2291160084","https://openalex.org/W2299467264","https://openalex.org/W2475334473","https://openalex.org/W2809624076","https://openalex.org/W2947737663","https://openalex.org/W2963122961","https://openalex.org/W2964182926","https://openalex.org/W2970601456","https://openalex.org/W2986514577","https://openalex.org/W2998218113","https://openalex.org/W4287118909","https://openalex.org/W6677580257","https://openalex.org/W6678914141","https://openalex.org/W6690026940","https://openalex.org/W6696798448","https://openalex.org/W6753069482","https://openalex.org/W6763737044","https://openalex.org/W6767298317","https://openalex.org/W6770169410","https://openalex.org/W6772230660","https://openalex.org/W6796815506"],"related_works":["https://openalex.org/W4390273403","https://openalex.org/W4386781444","https://openalex.org/W2150182025","https://openalex.org/W3092950680","https://openalex.org/W3197542405","https://openalex.org/W3204400881","https://openalex.org/W3214410901","https://openalex.org/W3204296682","https://openalex.org/W3183118997","https://openalex.org/W2917767146"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"based":[2],"recommender":[3,57,162],"systems":[4,163],"with":[5,131,164],"large":[6,161],"embedding":[7,74,124],"tables":[8,125],"have":[9],"become":[10],"pivotal":[11],"for":[12,34,52,89,102],"web":[13],"content":[14],"recommendation.":[15],"However,":[16],"the":[17,67,79,82,117,138,143,157,173],"growing":[18],"size":[19,129,159],"of":[20,25,160],"those":[21,72],"tables,":[22],"reaching":[23],"tens":[24],"gigabytes":[26],"or":[27],"even":[28],"terabytes,":[29],"presents":[30],"a":[31,45,165],"tough":[32],"challenge":[33],"conducting":[35],"inferences":[36],"on":[37,56,123],"resource-constrained":[38],"hardware.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,95],"present":[44],"novel":[46],"6-bit":[47,104],"fixed-point":[48],"number":[49,145],"representation":[50,146],"format":[51,61,147],"more":[53],"precise":[54],"quantization":[55,85,91,107,121,150],"models.":[58],"The":[59],"proposed":[60,118,144],"is":[62,87],"specifically":[63],"designed":[64],"to":[65,108,137],"accommodate":[66],"nonuniform":[68],"weight":[69],"distribution":[70],"inside":[71],"huge":[73],"tables.":[75],"To":[76],"further":[77],"alleviate":[78],"model":[80,128,158],"size,":[81],"well-known":[83],"K-means":[84],"technique":[86],"utilized":[88],"4-bit":[90,106],"and":[92,105,148,154],"beyond.":[93],"Moreover,":[94],"also":[96],"propose":[97],"dedicated":[98],"hardware":[99],"decoder":[100],"architectures":[101],"both":[103],"ensure":[109],"efficient":[110],"runtime":[111],"inference.":[112],"Experimental":[113],"results":[114],"show":[115],"that":[116],"low-bit":[119,149],"(8~3-bit)":[120],"techniques":[122,151],"yield":[126],"4~10.7x":[127],"reduction":[130],"minor":[132],"accuracy":[133,174],"loss":[134,175],"as":[135],"compared":[136],"original":[139],"FP32":[140],"model.":[141],"Therefore,":[142],"can":[152],"effectively":[153],"drastically":[155],"reduce":[156],"very":[166],"low":[167],"area":[168],"cost":[169],"while":[170],"still":[171],"keeping":[172],"minimized.":[176]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}
