{"id":"https://openalex.org/W4404133759","doi":"https://doi.org/10.1145/3649329.3655951","title":"MoNDE: Mixture of Near-Data Experts for Large-Scale Sparse Models","display_name":"MoNDE: Mixture of Near-Data Experts for Large-Scale Sparse Models","publication_year":2024,"publication_date":"2024-06-23","ids":{"openalex":"https://openalex.org/W4404133759","doi":"https://doi.org/10.1145/3649329.3655951"},"language":"en","primary_location":{"id":"doi:10.1145/3649329.3655951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655951","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3649329.3655951","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052772578","display_name":"Taehyun Kim","orcid":"https://orcid.org/0000-0003-3005-2066"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Taehyun Kim","raw_affiliation_strings":["Inter-University Semiconductor Research Center, Seoul, Seoul, Republic of Korea","Seoul National University, Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Inter-University Semiconductor Research Center, Seoul, Seoul, Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Seoul National University, Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101696051","display_name":"Kwanseok Choi","orcid":"https://orcid.org/0009-0000-1570-4463"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanseok Choi","raw_affiliation_strings":["Seoul National University, Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102987874","display_name":"Youngmock Cho","orcid":"https://orcid.org/0009-0005-4091-6907"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Youngmock Cho","raw_affiliation_strings":["Inter-University Semiconductor Research Center, Seoul, Seoul, Republic of Korea","Seoul National University, Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Inter-University Semiconductor Research Center, Seoul, Seoul, Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Seoul National University, Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110169553","display_name":"J. H. Cho","orcid":"https://orcid.org/0009-0003-6853-368X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehoon Cho","raw_affiliation_strings":["Seoul National University, Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102861073","display_name":"Hyuk-Jae Lee","orcid":"https://orcid.org/0000-0001-8895-9117"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyuk-Jae Lee","raw_affiliation_strings":["Inter-University Semiconductor Research Center, Seoul, Seoul, Republic of Korea","Seoul National University, Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Inter-University Semiconductor Research Center, Seoul, Seoul, Republic of Korea","institution_ids":[]},{"raw_affiliation_string":"Seoul National University, Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004251886","display_name":"Jaewoong Sim","orcid":"https://orcid.org/0000-0002-0403-9928"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewoong Sim","raw_affiliation_strings":["Seoul National University, Seoul, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5052772578"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":1.8421,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87141576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9939000010490417,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9939000010490417,"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/T11106","display_name":"Data Management and Algorithms","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6308577060699463},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6246368288993835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3521147668361664},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34129172563552856},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07570195198059082},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.059797078371047974}],"concepts":[{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6308577060699463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6246368288993835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3521147668361664},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34129172563552856},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07570195198059082},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.059797078371047974}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649329.3655951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655951","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3649329.3655951","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649329.3655951","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st ACM/IEEE Design Automation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2034861439","https://openalex.org/W3205803342"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Mixture-of-Experts":[0],"(MoE)":[1],"large":[2],"language":[3],"models":[4],"(LLM)":[5],"have":[6],"memory":[7,14,75],"requirements":[8],"that":[9,43],"often":[10],"exceed":[11],"the":[12,24,51,60,64,68,73,79,86,104],"GPU":[13,25],"capacity,":[15],"requiring":[16],"costly":[17],"parameter":[18,55,106],"movement":[19,56],"from":[20],"secondary":[21],"memories":[22],"to":[23,63],"for":[26,109],"expert":[27,83],"computation.":[28],"In":[29],"this":[30],"work,":[31],"we":[32],"present":[33],"Mixture":[34],"of":[35,53,81,88],"Near-Data":[36],"Experts":[37],"(MoNDE),":[38],"a":[39],"near-data":[40],"computing":[41,67],"solution":[42],"efficiently":[44],"enables":[45,92],"MoE":[46,54,96],"LLM":[47],"inference.":[48],"MoNDE":[49,91],"reduces":[50],"volume":[52],"by":[57],"transferring":[58],"only":[59],"hot":[61],"experts":[62,71],"GPU,":[65],"while":[66],"remaining":[69],"cold":[70],"inside":[72],"host":[74],"device.":[76],"By":[77],"replacing":[78],"transfers":[80],"massive":[82],"parameters":[84],"with":[85],"ones":[87],"small":[89],"activations,":[90],"far":[93],"more":[94],"communication-efficient":[95],"inference,":[97],"thereby":[98],"resulting":[99],"in":[100],"substantial":[101],"speedups":[102],"over":[103],"existing":[105],"of-floading":[107],"frameworks":[108],"both":[110],"encoder":[111],"and":[112],"decoder":[113],"operations.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}