Federal learning system using synonymous data
The invention provides a federal learning system using synonymous data. The federal learning system comprises a coordination device and a plurality of client devices. Each client device comprises an encoder which encodes the private data into an abstract, and the client device trains a client model...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | CHEN WEICHAO XU ZHIFAN ZHANG MINGQING |
| description | The invention provides a federal learning system using synonymous data. The federal learning system comprises a coordination device and a plurality of client devices. Each client device comprises an encoder which encodes the private data into an abstract, and the client device trains a client model according to the private data, the abstract and the general model and sends parameters of the abstract and the client model to the coordination device. The coordinating device is in communication connection with each client device and comprises a synonymous data generator. The coordination device sends the general model to each client device and determines an absent client device. The synonymous data generator generates synonymous data according to the abstract of the absent client device. The coordination device trains a substitution model according to the synonymous data and the abstract of the absent client device, and executes an aggregation operation according to the substitution model and the client model of |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116796863A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116796863A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116796863A3</originalsourceid><addsrcrecordid>eNrjZNB1S01JLUrMUchJTSzKy8xLVyiuLC5JzVUoLYZw8vLzKnPzS4sVUhJLEnkYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyal5qSbyzn6GhmbmlmYWZsaMxMWoA8rgqrg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Federal learning system using synonymous data</title><source>esp@cenet</source><creator>CHEN WEICHAO ; XU ZHIFAN ; ZHANG MINGQING</creator><creatorcontrib>CHEN WEICHAO ; XU ZHIFAN ; ZHANG MINGQING</creatorcontrib><description>The invention provides a federal learning system using synonymous data. The federal learning system comprises a coordination device and a plurality of client devices. Each client device comprises an encoder which encodes the private data into an abstract, and the client device trains a client model according to the private data, the abstract and the general model and sends parameters of the abstract and the client model to the coordination device. The coordinating device is in communication connection with each client device and comprises a synonymous data generator. The coordination device sends the general model to each client device and determines an absent client device. The synonymous data generator generates synonymous data according to the abstract of the absent client device. The coordination device trains a substitution model according to the synonymous data and the abstract of the absent client device, and executes an aggregation operation according to the substitution model and the client model of</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230922&DB=EPODOC&CC=CN&NR=116796863A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230922&DB=EPODOC&CC=CN&NR=116796863A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN WEICHAO</creatorcontrib><creatorcontrib>XU ZHIFAN</creatorcontrib><creatorcontrib>ZHANG MINGQING</creatorcontrib><title>Federal learning system using synonymous data</title><description>The invention provides a federal learning system using synonymous data. The federal learning system comprises a coordination device and a plurality of client devices. Each client device comprises an encoder which encodes the private data into an abstract, and the client device trains a client model according to the private data, the abstract and the general model and sends parameters of the abstract and the client model to the coordination device. The coordinating device is in communication connection with each client device and comprises a synonymous data generator. The coordination device sends the general model to each client device and determines an absent client device. The synonymous data generator generates synonymous data according to the abstract of the absent client device. The coordination device trains a substitution model according to the synonymous data and the abstract of the absent client device, and executes an aggregation operation according to the substitution model and the client model of</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNB1S01JLUrMUchJTSzKy8xLVyiuLC5JzVUoLYZw8vLzKnPzS4sVUhJLEnkYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyal5qSbyzn6GhmbmlmYWZsaMxMWoA8rgqrg</recordid><startdate>20230922</startdate><enddate>20230922</enddate><creator>CHEN WEICHAO</creator><creator>XU ZHIFAN</creator><creator>ZHANG MINGQING</creator><scope>EVB</scope></search><sort><creationdate>20230922</creationdate><title>Federal learning system using synonymous data</title><author>CHEN WEICHAO ; XU ZHIFAN ; ZHANG MINGQING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116796863A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN WEICHAO</creatorcontrib><creatorcontrib>XU ZHIFAN</creatorcontrib><creatorcontrib>ZHANG MINGQING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN WEICHAO</au><au>XU ZHIFAN</au><au>ZHANG MINGQING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Federal learning system using synonymous data</title><date>2023-09-22</date><risdate>2023</risdate><abstract>The invention provides a federal learning system using synonymous data. The federal learning system comprises a coordination device and a plurality of client devices. Each client device comprises an encoder which encodes the private data into an abstract, and the client device trains a client model according to the private data, the abstract and the general model and sends parameters of the abstract and the client model to the coordination device. The coordinating device is in communication connection with each client device and comprises a synonymous data generator. The coordination device sends the general model to each client device and determines an absent client device. The synonymous data generator generates synonymous data according to the abstract of the absent client device. The coordination device trains a substitution model according to the synonymous data and the abstract of the absent client device, and executes an aggregation operation according to the substitution model and the client model of</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116796863A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Federal learning system using synonymous data |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T16%3A21%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=CHEN%20WEICHAO&rft.date=2023-09-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116796863A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |