{"id":"https://openalex.org/W4386486780","doi":"https://doi.org/10.1145/3600061.3603136","title":"Training ChatGPT-like Models with In-network Computation","display_name":"Training ChatGPT-like Models with In-network Computation","publication_year":2023,"publication_date":"2023-06-29","ids":{"openalex":"https://openalex.org/W4386486780","doi":"https://doi.org/10.1145/3600061.3603136"},"language":"en","primary_location":{"id":"doi:10.1145/3600061.3603136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3600061.3603136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Asia-Pacific Workshop on Networking","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/A5103230878","display_name":"Shuhao Fu","orcid":"https://orcid.org/0009-0005-3303-3882"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuhao Fu","raw_affiliation_strings":["University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051983841","display_name":"Yong Liao","orcid":"https://orcid.org/0000-0001-6403-0557"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liao","raw_affiliation_strings":["University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004288865","display_name":"Pengyuan Zhou","orcid":"https://orcid.org/0000-0002-7909-4059"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhou","raw_affiliation_strings":["University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103230878"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11153086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"206","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9988999962806702,"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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","score":0.9988999962806702,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9988999962806702,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7371147274971008},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7228255867958069},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6258944272994995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35088762640953064},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10528972744941711}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371147274971008},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7228255867958069},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6258944272994995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35088762640953064},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10528972744941711},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3600061.3603136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3600061.3603136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th Asia-Pacific Workshop on Networking","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/18acdb9e-c6c8-41e2-be50-fe41769ee7a0","is_oa":false,"landing_page_url":"https://pure.au.dk/portal/en/publications/18acdb9e-c6c8-41e2-be50-fe41769ee7a0","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fu , S , Liao , Y & Zhou , P 2023 , Training ChatGPT-like Models with In-network Computation . in Proceedings of the 7th Asia-Pacific Workshop on Networking, APNET 2023 . Association for Computing Machinery, Inc. , pp. 206-207 , 7th Asia-Pacific Workshop on Networking, APNET 2023 , Hong Kong , China , 29/06/2023 . https://doi.org/10.1145/3600061.3603136","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2983123278","https://openalex.org/W3025935268","https://openalex.org/W3189259198","https://openalex.org/W3198137461"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2810751659"],"abstract_inverted_index":{"ChatGPT":[0],"shows":[1,44],"the":[2,15,26],"enormous":[3],"potential":[4],"of":[5,17,19],"large":[6],"language":[7],"models":[8,11],"(LLMs).":[9],"These":[10],"can":[12],"easily":[13],"reach":[14],"size":[16],"billions":[18],"parameters":[20],"and":[21],"create":[22],"training":[23],"difficulties":[24],"for":[25],"majority.":[27],"We":[28],"propose":[29],"a":[30,54],"paradigm":[31],"to":[32,50],"train":[33],"LLMs":[34,49],"using":[35],"distributed":[36],"in-network":[37],"computation":[38],"on":[39],"routers.":[40],"Our":[41],"preliminary":[42],"result":[43],"that":[45],"our":[46],"design":[47],"allows":[48],"be":[51],"trained":[52],"at":[53],"reasonable":[55],"learning":[56],"rate":[57],"without":[58],"demanding":[59],"extensive":[60],"GPU":[61],"resources.":[62]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}