EDITING A TARGET MODEL TO FORGET DATA SAMPLES USING A REFERENCE MODEL TO ADJUST WEIGHTS OF THE TARGET MODEL
Provided are a computer program product, system, and method for editing a target model to forget data samples. Forget data samples of data samples to forget are inputted into a reference model, trained on a non-private data set, to produce reference output. The forget data samples to forget are inpu...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | English |
Published |
29.08.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Provided are a computer program product, system, and method for editing a target model to forget data samples. Forget data samples of data samples to forget are inputted into a reference model, trained on a non-private data set, to produce reference output. The forget data samples to forget are inputted to a target model, trained on a total data set comprising the non-private data set and a private data set, to produce target output. The private data set includes the forget data samples A loss function is calculated to measure a divergence of the reference output and the target output. A determination is made of gradients that minimize an error of the loss function. Optimized gradients are calculated from the determined gradients. The optimized gradients are applied to update weights in the target model to produce an edited target model. |
---|---|
AbstractList | Provided are a computer program product, system, and method for editing a target model to forget data samples. Forget data samples of data samples to forget are inputted into a reference model, trained on a non-private data set, to produce reference output. The forget data samples to forget are inputted to a target model, trained on a total data set comprising the non-private data set and a private data set, to produce target output. The private data set includes the forget data samples A loss function is calculated to measure a divergence of the reference output and the target output. A determination is made of gradients that minimize an error of the loss function. Optimized gradients are calculated from the determined gradients. The optimized gradients are applied to update weights in the target model to produce an edited target model. |
Author | SHMELKIN, Ron GOLDSTEEN, Abigail ZOHAR, Tal FARKASH, Ariel |
Author_xml | – fullname: FARKASH, Ariel – fullname: SHMELKIN, Ron – fullname: GOLDSTEEN, Abigail – fullname: ZOHAR, Tal |
BookMark | eNqNzD0LwjAUheEMOvj1Hy44C5qK6HhpbppI20hyi2MpEhelLdT_j6CCuDkdXng4UzFquzZOxI2UZVtmgMDoM2IonKIc2IF2r1bICAGLU04BqvC2njR5KlP6clTHKjCcyWaGAzgNbOjndC7G1-Y-xMVnZ2KpiVOzin1Xx6FvLrGNj7oKci23cn_YyQQ3yX_qCY16OGQ |
ContentType | Patent |
DBID | EVB |
DatabaseName | esp@cenet |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Chemistry Sciences Physics |
ExternalDocumentID | US2024289623A1 |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_US2024289623A13 |
IEDL.DBID | EVB |
IngestDate | Fri Sep 27 05:22:25 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_US2024289623A13 |
Notes | Application Number: US202318176068 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240829&DB=EPODOC&CC=US&NR=2024289623A1 |
ParticipantIDs | epo_espacenet_US2024289623A1 |
PublicationCentury | 2000 |
PublicationDate | 20240829 |
PublicationDateYYYYMMDD | 2024-08-29 |
PublicationDate_xml | – month: 08 year: 2024 text: 20240829 day: 29 |
PublicationDecade | 2020 |
PublicationYear | 2024 |
RelatedCompanies | INTERNATIONAL BUSINESS MACHINES CORPORATION |
RelatedCompanies_xml | – name: INTERNATIONAL BUSINESS MACHINES CORPORATION |
Score | 3.5677612 |
Snippet | Provided are a computer program product, system, and method for editing a target model to forget data samples. Forget data samples of data samples to forget... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
Title | EDITING A TARGET MODEL TO FORGET DATA SAMPLES USING A REFERENCE MODEL TO ADJUST WEIGHTS OF THE TARGET MODEL |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240829&DB=EPODOC&locale=&CC=US&NR=2024289623A1 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEL8Q_HxT1PiBpolmb4syxpgPxIy1YxBgZOuUN7LPxGgGkRn_fa8NCL7weB-5tE2u19_12gN40DITw4ZmqLrZaKp6bj6pUZIYahKL_tq5mTZyWSA7NtxQH0xb0wp8rt_CyH9Cf-TniOhRCfp7KffrxSaJRWVt5fIxfkfW_MXhHaqs0LEm2ycrtNthE496tmLbnTBQxr6UIbbAYG8hVtrDg3RbFICx1654l7LYDirOCexP0F5RnkIlK2pwZK97r9XgcLS68q7BgazRTJbIXPnh8gw-GO3z_rhHLMItv8c4GXmUDQn3CKI6QVOLWySwRpMhC4jorSF0feYwX-SUNuoWHYQBJ2-s33N5QDyHcJf9M3oO9w7jtqvi-Gd_yzULg-3JNi-gWsyL7BKImelZnKd6kiLoilIjjvQ0brUbaYKgKY_TK6jvsnS9W3wDx4IU-VbtuQ7V8us7u8WAXcZ3cp1_Ab0qkD4 |
link.rule.ids | 230,309,783,888,25578,76886 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEL8Q_MA3RY0fqE00e1uUMeZ8IGasHRvug2yd8kbYV2I0g8iM_75tA4IvPPauubSXXK-_610P4E7JdeY2FE1W9XZHVgv9QZ6mqSanCe-vXehZuxAJsr5mx-pw3B3X4HNVCyP-Cf0RnyMyi0qZvVfivJ6vg1hY5FYu7pN3Rpo9W7SHpSU6VkT7ZAn3e2QU4MCUTLMXR5IfCh7DFszZGwwr7bBLts7tgbz2eV3KfNOpWIewO2LyyuoIannZhIa56r3WhH1v-eTdhD2Ro5kuGHFph4tj-CDYoY4_QAaiRjggFHkBJi6iAWKojo-xQQ0UGd7IJRHivTX43JBYJOQxpfV0Aw_jiKI34gxsGqHAQtQm_4SewK1FqGnLbP2TP3VN4mhzs51TqJezMj8DpOdqnhSZmmYMdE0zLZmqWdJ9bGcpA01Fkp1Da5uki-3sG2jY1HMnruO_XMIBZ_HYq_LUgnr19Z1fMeddJddC57-ss5Mw |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=EDITING+A+TARGET+MODEL+TO+FORGET+DATA+SAMPLES+USING+A+REFERENCE+MODEL+TO+ADJUST+WEIGHTS+OF+THE+TARGET+MODEL&rft.inventor=FARKASH%2C+Ariel&rft.inventor=SHMELKIN%2C+Ron&rft.inventor=GOLDSTEEN%2C+Abigail&rft.inventor=ZOHAR%2C+Tal&rft.date=2024-08-29&rft.externalDBID=A1&rft.externalDocID=US2024289623A1 |