{"id":"https://openalex.org/W4404133929","doi":"https://doi.org/10.1145/3649329.3657374","title":"FastQuery: Communication-efficient Embedding Table Query for Private LLMs inference","display_name":"FastQuery: Communication-efficient Embedding Table Query for Private LLMs inference","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404133929","doi":"https://doi.org/10.1145/3649329.3657374"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3657374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3657374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","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/A5102678193","display_name":"Chenqi Lin","orcid":"https://orcid.org/0009-0009-6575-2194"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenqi Lin","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100949672","display_name":"Tianshi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshi Xu","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114950458","display_name":"Zebin Yang","orcid":"https://orcid.org/0009-0007-0672-6389"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zebin Yang","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002760019","display_name":"Runsheng Wang","orcid":"https://orcid.org/0000-0002-7514-0767"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runsheng Wang","raw_affiliation_strings":["Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062886480","display_name":"Ru Huang","orcid":"https://orcid.org/0000-0002-8146-4821"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ru Huang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100457502","display_name":"Meng Li","orcid":"https://orcid.org/0000-0002-7212-2264"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Li","raw_affiliation_strings":["Institute for Artificial Intelligence and School of Integrated Circuits, Peking University, Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence and School of Integrated Circuits, Peking University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102678193"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17708773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10237","display_name":"Cryptography and Data Security","score":0.9983000159263611,"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/T10237","display_name":"Cryptography and Data Security","score":0.9983000159263611,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.998199999332428,"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/T11719","display_name":"Data Quality and Management","score":0.9273999929428101,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7077600955963135},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6589387059211731},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6455184817314148},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5660656094551086},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.43655940890312195},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3386719822883606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2722064256668091},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2486535608768463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077600955963135},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6589387059211731},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6455184817314148},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5660656094551086},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.43655940890312195},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3386719822883606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2722064256668091},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2486535608768463}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3657374","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649329.3657374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2907648450","https://openalex.org/W3133749795","https://openalex.org/W4321393203","https://openalex.org/W4386764044","https://openalex.org/W4408750063","https://openalex.org/W6778883912","https://openalex.org/W6784109961"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W4394360958","https://openalex.org/W2037549926","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2055243143","https://openalex.org/W2849310602","https://openalex.org/W3006008237"],"abstract_inverted_index":{"With":[0],"the":[1,61,66,70,78,81,122],"fast":[2],"evolution":[3],"of":[4,68,73,80],"large":[5],"language":[6],"models":[7],"(LLMs),":[8],"privacy":[9],"concerns":[10],"with":[11],"user":[12,33,74],"queries":[13,75],"arise":[14],"as":[15,45],"they":[16],"may":[17],"contain":[18],"sensitive":[19],"information.":[20],"Private":[21],"inference":[22],"based":[23],"on":[24,156],"homomorphic":[25],"encryption":[26],"(HE)":[27],"has":[28,41],"been":[29],"proposed":[30],"to":[31,42,84,118,128],"protect":[32],"query":[34,40,99],"privacy.":[35],"However,":[36],"private":[37,96],"embedding":[38,82,97,108],"table":[39,83,98,109],"be":[43],"formulated":[44],"a":[46,95,106,113],"HE-based":[47,130],"matrix-vector":[48],"multiplication":[49],"problem":[50],"and":[51,56,76,112,124,135,147,159],"suffers":[52],"from":[53,65],"enormous":[54],"computation":[55,123],"communication":[57,125,153],"overhead.":[58],"We":[59],"observe":[60],"overhead":[62],"mainly":[63],"comes":[64],"neglect":[67],"1)":[69],"one-hot":[71],"nature":[72],"2)":[77],"robustness":[79],"low":[85],"bit-width":[86],"quantization":[87,110],"noise.":[88],"Hence,":[89],"in":[90],"this":[91],"paper,":[92],"we":[93],"propose":[94],"optimization":[100],"framework,":[101],"dubbed":[102],"FastQuery.":[103],"FastQuery":[104,137],"features":[105],"communication-aware":[107],"algorithm":[111,117],"one-hot-aware":[114],"dense":[115],"packing":[116],"simultaneously":[119],"reduce":[120],"both":[121,157],"costs.":[126],"Compared":[127],"prior-art":[129],"frameworks,":[131],"e.g.,":[132],"Cheetah,":[133],"Iron,":[134],"Bumblebee,":[136],"achieves":[138],"more":[139,148],"than":[140,149],"4.3\u00d7,":[141],"2.7\u00d7,":[142],"1.3\u00d7":[143],"latency":[144],"reduction,":[145,154],"respectively":[146],"75.7\u00d7,":[150],"60.2\u00d7,":[151],"20.2\u00d7":[152],"respectively,":[155],"LLAMA-7B":[158],"LLAMA-30B.":[160]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}