Differentielle Private Vertrauliche Verknüpfung von Daten Beim Modelltraining

Details

Veröffentlichungs-Nr.

EP4726609

Anmeldetag

10. Oktober 2025

Veröffentlichung

15. April 2026

Rechtsraum

EP

IPC

G06N3/084, G06N20/00(PETERSON DANIEL et al.)

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training machine learning models using data of multiple entities without compromising the precise joining/alignment of the data. In one aspect, a method includes obtaining two or more datasets, wherein each dataset is received from a different entity that maintains the dataset. The two or more datasets are joined using a set of keys. A loss function for training a machine learning model is generated based on inputs comprising the joined two or more datasets, the machine learning model including multiple model parameters. Noise is injected into one or more derivatives computed from the loss function, the inputs, or both. The model parameters are updated using the noised one or more derivatives.

Anmelder

Firma

GOOGLE LLC

Land

🇺🇸 USA

Fachgebiete