Training user-level differentially private machine-learned models
US11726769B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 12, 2022 |
| Grant date | Aug 15, 2023 |
| Priority date | — |
| Expiry date | Oct 12, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/95
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods for learning differentially private machine-learned models are provided. A computing system can include one or more server computing devices comprising one or more processors and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors cause the one or more server computing devices to perform operations. The operations can include selecting a subset of client computing devices from a pool of available client computing devices; providing a machine-learned model to the selected client computing devices; receiving, from each selected client computing device, a local update for the machine-learned model; determining a differentially private aggregate of the local updates; and determining an updated machine-learned model based at least in part on the data-weighted average of the local updates.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.