METHOD AND APPARATUS FOR STOCHASTIC INFERENCE BETWEEN MULTIPLE RANDOM VARIABLES VIA COMMON REPRESENTATION

• US 20200134499A1
• Filed: 04/03/2019
• Published: 04/30/2020
• Est. Priority Date: 10/26/2018
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: RYU, Jongha, CHOI, Yoo Jin, EL-KHAMY, Mostafa, LEE, Jungwon
• Granted Patent: US 11,620,555 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/045 Combinations of networks
• CPC Class Codes: G06N 3/047 Probabilistic or stochastic networks
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A method and system are herein disclosed. The method includes developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables, generating a variational posterior of the joint latent variable model, training the variational posterior, and performing inference of the first variable from the second variable based on the variational posterior.

Claims

1. A method, comprising:

developing a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables;

generating a variational posterior of the joint latent variable model;

training the variational posterior; and

performing inference of the first variable from the second variable based on the variational posterior.

2. The method of claim 1, further comprising extracting common information between the first variable and the second variable.

3. The method of claim 2, wherein extracting common information comprises adding a regularization term to a loss function.

4. The method of claim 1, further comprising adding local randomness to the joint latent variable model.

5. The method of claim 4, wherein adding local randomness further comprises separating the joint latent variable into a common latent variable and a local latent variable.

6. The method of claim 4, wherein performing inference comprises conditionally generating the first variable from the second variable.

7. The method of claim 4, wherein performing inference comprises generating a style for the first variable or the second variable.

8. The method of claim 1, wherein training the variational posterior comprises training a decoder in the joint latent variable model with a full approximate posterior of the joint latent variable model.

9. The method of claim 8, wherein training the variational posterior further comprises fixing parameters of the decoder and training the marginal variational posterior with the trained decoder.

10. The method of claim 1, wherein training the variational posterior comprises training the joint latent variable model, a full approximate posterior, and the marginal variational posterior jointly using a hyperparameter.

11. A system, comprising:

at least one decoder;

at least one encoder; and

a processor configured to;

develop a joint latent variable model having a first variable, a second variable, and a joint latent variable representing common information between the first and second variables;

generate a variational posterior of the joint latent variable model;

train the variational posterior; and

perform inference of the first variable from the second variable based on the variational posterior.

12. The system of claim 11, wherein the processor is further configured to extract common information between the first variable and the second variable.

13. The system of claim 12, wherein the processor is configured to extract common information comprises by adding a regularization term to a loss function.

14. The system of claim 11, wherein the processor is further configured to add local randomness to the joint latent variable model.

15. The system of claim 14, wherein the processor is configured to add local randomness by separating the joint latent variable into a common latent variable and a local latent variable.

16. The system of claim 14, wherein the processor is further configured to perform inference by conditionally generating the first variable from the second variable.

17. The system of claim 14, wherein the processor is further configured to perform inference by generating a style for the first variable or the second variable.

18. The system of claim 11, wherein the processor is configured to train the variational posterior by training the at least one decoder in the joint latent variable model with a full approximate posterior of the joint latent variable model.

19. The system of claim 18, wherein the processor is further configured to train the variational posterior by fixing parameters of the at least one decoder and training the marginal variational posterior with the trained at least one decoder.

20. The system of claim 11, wherein the processor is further configured to train the marginal variational posterior by training the joint latent variable model, a full approximate posterior, and the variational posterior jointly using a hyperparameter.