{"id":"https://openalex.org/W4392945099","doi":"https://doi.org/10.1109/iceic61013.2024.10457210","title":"Analyzing the Scaling Characteristics of Transformer Feed-Forward Networks for the Trillion-Parameter Era and Beyond","display_name":"Analyzing the Scaling Characteristics of Transformer Feed-Forward Networks for the Trillion-Parameter Era and Beyond","publication_year":2024,"publication_date":"2024-01-28","ids":{"openalex":"https://openalex.org/W4392945099","doi":"https://doi.org/10.1109/iceic61013.2024.10457210"},"language":"en","primary_location":{"id":"doi:10.1109/iceic61013.2024.10457210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic61013.2024.10457210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","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/A5100438965","display_name":"Tae-Hyun Kim","orcid":"https://orcid.org/0000-0001-5229-2736"},"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":["ISRC, Seoul National University,Dept. of ECE,Seoul,Republic of Korea","Dept. of ECE, ISRC, Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"ISRC, Seoul National University,Dept. of ECE,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of ECE, ISRC, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024723558","display_name":"Hyuk\u2010Jae Lee","orcid":"https://orcid.org/0000-0001-6811-9647"},"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":["ISRC, Seoul National University,Dept. of ECE,Seoul,Republic of Korea","Dept. of ECE, ISRC, Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"ISRC, Seoul National University,Dept. of ECE,Seoul,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of ECE, ISRC, Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100438965"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.1261,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.30347818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11222","display_name":"Magnetic Properties and Applications","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11222","display_name":"Magnetic Properties and Applications","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2504","display_name":"Electronic, Optical and Magnetic Materials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11343","display_name":"Power Transformer Diagnostics and Insulation","score":0.9549999833106995,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10511","display_name":"High voltage insulation and dielectric phenomena","score":0.9239000082015991,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6464693546295166},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5828293561935425},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48180264234542847},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.30305683612823486},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17909294366836548},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.16399267315864563},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15820041298866272}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6464693546295166},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5828293561935425},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48180264234542847},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.30305683612823486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17909294366836548},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.16399267315864563},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15820041298866272},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic61013.2024.10457210","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iceic61013.2024.10457210","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3015468748","https://openalex.org/W4384918448","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2864363823"],"abstract_inverted_index":{"Many":[0],"transformers-based":[1],"tasks":[2],"such":[3],"as":[4],"language":[5],"translation,":[6],"question":[7],"answering":[8],"and":[9,60,90],"code":[10],"generation":[11],"have":[12],"shown":[13],"increasingly":[14],"high":[15],"task":[16],"quality":[17],"over":[18],"the":[19,32,50,61,64,78],"recent":[20],"years.":[21],"This":[22],"has":[23,45,67],"been":[24,46,68],"made":[25],"possible":[26],"by":[27],"unprecedented":[28],"model":[29],"size,":[30],"i.e.,":[31],"number":[33],"of":[34,63,81],"parameters":[35],"that":[36],"consisting":[37],"each":[38],"DNN":[39],"model.":[40],"Until":[41],"recently,":[42],"much":[43],"research":[44],"centered":[47],"on":[48],"optimizing":[49],"attention":[51],"module,":[52],"whose":[53],"cost":[54,62,79],"increases":[55],"quadratically":[56],"to":[57,87],"sequence":[58],"length,":[59],"feed-forward":[65],"network":[66],"relatively":[69],"less":[70],"explored.":[71],"To":[72],"this":[73,75],"end,":[74],"paper":[76],"analyzes":[77],"profile":[80],"large":[82],"transformer":[83],"models":[84],"with":[85],"regard":[86],"embedding":[88],"size":[89],"suggests":[91],"optimization":[92],"directions.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
