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.

公开(公告)号：US11443202B2

公开(公告)日：2022-09-13

申请号：US16551829

申请日：2019-08-27

Applicant: Google LLC

Inventor： Manas Rajendra Joglekar ,  Jay Adams ,  Sujeet Bansal

IPC: G06N20/00 ,  G06N5/04 ,  G06F16/955 ,  G06N3/08

Abstract: The present disclosure is directed to systems and methods that include a machine-learned label embedding model that generates feature-based label embeddings for labels in real-time, in furtherance, for example, of selection of labels relative to a particular entity. In particular, one example computing system includes both a machine-learned entity embedding model configured to receive and process entity feature data descriptive of an entity to generate an entity embedding for the entity and a machine-learned label embedding model configured to receive and process first label feature data associated with a first label to generate a first label embedding for the first label.

公开(公告)号：US20210004693A1

公开(公告)日：2021-01-07

申请号：US16551829

申请日：2019-08-27

Applicant: Google LLC

Inventor： Manas Rajendra Joglekar ,  Jay Adams ,  Sujeet Bansal

IPC: G06N5/04 ,  G06N20/00 ,  G06F16/955

Abstract: The present disclosure is directed to systems and methods that include a machine-learned label embedding model that generates feature-based label embeddings for labels in real-time, in furtherance, for example, of selection of labels relative to a particular entity. In particular, one example computing system includes both a machine-learned entity embedding model configured to receive and process entity feature data descriptive of an entity to generate an entity embedding for the entity and a machine-learned label embedding model configured to receive and process first label feature data associated with a first label to generate a first label embedding for the first label.

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.