公开(公告)号：US20200372076A1

公开(公告)日：2020-11-26

申请号：US16878912

申请日：2020-05-20

Applicant: Google LLC

Inventor： Cong Li ,  Jay Adams ,  Manas Joglekar ,  Pranav Khaitan ,  Quoc V. Le ,  Mei Chen

IPC: G06F16/9035 ,  G06F40/242 ,  G06N3/08 ,  G06N20/00 ,  G06F11/34

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.

公开(公告)号：US20230146053A1

公开(公告)日：2023-05-11

申请号：US18076662

申请日：2022-12-07

Applicant: Google LLC

Inventor： Cong Li ,  Jay Adams ,  Manas Joglekar ,  Pranav Khaitan ,  Quoc V. Le ,  Mei Chen

IPC: G06F16/9035 ,  G06F40/242 ,  G06F11/34 ,  G06N20/00 ,  G06N3/08

CPC classification number: G06F16/9035 ,  G06F40/242 ,  G06F11/3466 ,  G06N20/00 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.

公开(公告)号：US11537664B2

公开(公告)日：2022-12-27

申请号：US16878912

申请日：2020-05-20

Applicant: Google LLC

Inventor： Cong Li ,  Jay Adams ,  Manas Joglekar ,  Pranav Khaitan ,  Quoc V. Le ,  Mei Chen

IPC: G06F16/9035 ,  G06F40/242 ,  G06F11/34 ,  G06N20/00 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.

公开(公告)号：US20250077871A1

公开(公告)日：2025-03-06

申请号：US18564160

申请日：2023-05-25

Applicant: Google LLC

Inventor： Devora Berlowitz ,  Steve Shaw-Tang Chien ,  Yunqi Xue ,  Lin Ning ,  Shuang Song ,  Mei Chen

IPC: G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for privacy-sensitive training of a neural network. In one aspect, a system comprises a central memory configured to store current values of a set of neural network parameters and one or more computers that are configured to implement a plurality of worker computing units, where each worker computing unit is configured to repeatedly perform operations comprising obtaining current values of the set of neural network parameters from the central memory, sampling a batch of network inputs from a set of training data, determining a respective gradient corresponding to each network input, determining an aggregated gradient based on the gradients, identifying a subset of a set of gradient values as target values, generating a noisy gradient by combining random noise with the target gradient values, and updating the current values of the set of neural network parameters.

公开(公告)号：US11714857B2

公开(公告)日：2023-08-01

申请号：US18076662

申请日：2022-12-07

Applicant: Google LLC

Inventor： Cong Li ,  Jay Adams ,  Manas Joglekar ,  Pranav Khaitan ,  Quoc V. Le ,  Mei Chen

IPC: G06F16/9035 ,  G06F40/242 ,  G06F11/34 ,  G06N20/00 ,  G06N3/08

CPC classification number: G06F16/9035 ,  G06F11/3466 ,  G06F40/242 ,  G06N3/08 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining, for each of one or more categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active during processing of inputs by a machine learning model. In one aspect, a method comprises: generating a batch of output sequences, each output sequence in the batch specifying, for each of the categorical features, a respective vocabulary of categorical feature values of the categorical feature that should be active; for each output sequence in the batch, determining a performance metric of the machine learning model on a machine learning task after the machine learning model has been trained to perform the machine learning task with only the respective vocabulary of categorical feature values of each categorical feature specified by the output sequence being active.