US Patent Application 18344188. MACHINE LEARNING MODEL UPDATE METHOD AND APPARATUS simplified abstract
Contents
MACHINE LEARNING MODEL UPDATE METHOD AND APPARATUS
Organization Name
Inventor(s)
MACHINE LEARNING MODEL UPDATE METHOD AND APPARATUS - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18344188 Titled 'MACHINE LEARNING MODEL UPDATE METHOD AND APPARATUS'
Simplified Explanation
This abstract describes a method for updating a machine learning model using encrypted intermediate results. The method involves two apparatuses, where the first apparatus generates a result based on a subset of data and receives an encrypted result from the second apparatus, which is generated based on a different subset of data. The first apparatus then obtains a gradient of a model based on the two intermediate results, which is used to update the model after being decrypted using a private key generated by the second apparatus. The method utilizes homomorphic encryption to ensure the privacy of the data during the model update process.
Original Abstract Submitted
Embodiments of this application provide a machine learning model update method, applied to the field of artificial intelligence. The method includes: A first apparatus generates a first intermediate result based on a first data subset. The first apparatus receives an encrypted second intermediate result sent by a second apparatus, where the second intermediate result is generated based on a second data subset corresponding to the second apparatus. The first apparatus obtains a first gradient of a first model, where the first gradient of the first model is generated based on the first intermediate result and the encrypted second intermediate result. After being decrypted by using a second private key, the first gradient of the first model is for updating the first model, where the second private key is a decryption key generated by the second apparatus for homomorphic encryption.