Google Inc.

Om Dipakbhai Thakkar

Rajiv Mathews

Françoise Beaufays

Andrew Hard

Swaroop Indra Ramaswamy

Francoise Beaufays

Ehsan Amid

Peter Kairouz

Brendan McMahan

Abhradeep Guha Thakurta

Borja De Balle Pigem

W Ronny Huang

Hakim Sidahmed

Florian Tramèr

Techniques are disclosed that enable training a global model using gradients provided to a remote system by a set of client devices during a reporting window, where each client device randomly determines a reporting time in the reporting window to provide the gradient to the remote system. Various implementations include each client device determining a corresponding gradient by processing data using a local model stored locally at the client device, where the local model corresponds to the global model.

Server efficient enhancement of privacy in federated learning

A method of phrase extraction for ASR models includes obtaining audio data characterizing an utterance and a corresponding ground-truth transcription of the utterance and modifying the audio data to obfuscate a particular phrase recited in the utterance. The method also includes processing, using a trained ASR model, the modified audio data to generate a predicted transcription of the utterance, and determining whether the predicted transcription includes the particular phrase by comparing the predicted transcription of the utterance to the ground-truth transcription of the utterance. When the predicted transcription includes the particular phrase, the method includes generating an output indicating that the trained ASR model leaked the particular phrase from a training data set used to train the ASR model.

Phrase extraction for ASR models

Implementations disclosed herein are directed to federated learning of machine learning ('ML') model(s) based on gradient(s) generated at corresponding client devices and a remote system. Processor(s) of the corresponding client devices can process client data generated locally at the corresponding client devices using corresponding on-device ML model(s) to generate corresponding predicted outputs, generate corresponding client gradients based on the corresponding predicted outputs, and transmit the corresponding client gradients to the remote system. Processor(s) of the remote system can process remote data obtained from remote database(s) using global ML model(s) to generate additional corresponding predicted outputs, generate corresponding remote gradients based on the additional corresponding predicted outputs. Further, the remote system can utilize the corresponding client gradients and the corresponding remote gradients to update the global ML model(s) or weights thereof. The updated global ML model(s) and/or the updated weights thereof can be transmitted back to the corresponding client devices.

Mixed client-server federated learning of machine learning model(s)

Growing community of inventors

San Jose, CA, United States of America

Om Dipakbhai Thakkar