Adversarial multi-binary neural network for multi-class classification

1. A multi-class classification system, comprising:

at least one processor; and

at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:

training a multi-class classifier based on calculating a shared representation and an adversarial loss;

applying the multi-class classifier to classify a set of objects into multiple classes, wherein the set of objects comprise textual objects including a word or a sentence;

applying a plurality of binary classifiers to the set of objects, wherein the plurality of binary classifiers are decomposed from the multi-class classifier, each binary classifier classifying the set of the objects into a first group consisting of one or more classes selected from the multiple classes and a second group consisting of one or more remaining classes of the multiple classes; and

jointly classifying the set of objects using the multi-class classifier and the plurality of binary classifiers.

2. The system of claim 1 , wherein the operations comprise:

jointly training the multi-class classifier and the plurality of binary classifiers by minimizing a joint loss comprising a multi-class classification loss corresponding to the multi-class classifier and one or more binary classification losses corresponding to one or more binary classifiers selected from the plurality of binary classifiers.

3. The system of claim 1 , wherein the operations comprise:

receiving, by an encoder corresponding to at least one binary classifier, the set of objects; and

generating, by the encoder, contextual information from the set of the objects.

4. The system of claim 3 , wherein the encoder comprises a bidirectional long short memory (BiLSTM).

5. The system of claim 3 , wherein the operations further comprise:

determining, by a private attention layer corresponding to the at least one binary classifier, class-specific information based on the contextual information; and

determining, by a shared attention layer, class-agnostic information based on the contextual information.

6. The system of claim 5 , wherein the class-agnostic information comprises a shared feature shared by multiple classes.

7. The system of claim 5 , wherein the operations comprise:

refining, by a discriminator, the class-agnostic information by minimizing the adversarial loss.

8. The system of claim 7 , wherein the operations comprise:

jointly training the multi-class classifier and the plurality of binary classifiers by minimizing a joint loss comprising:

a multi-class classification loss corresponding to the multi-class classifier;

one or more binary classification losses corresponding to one or more binary classifiers selected from the plurality of binary classifiers; and

the adversarial loss.

9. The system of claim 5 , wherein the operations comprise:

generating classification features of the at least one binary classifier by concatenating the class-specific information and the class-agnostic information.

10. The system of claim 5 , wherein the operations comprise:

generating classification features of the multi-class classifier by concatenating class-specific information corresponding to multiple binary classifiers and the class-agnostic information.

11. A multi-class classification method, comprising:

training a multi-class classifier based on calculating a shared representation and an adversarial loss;

applying the multi-class classifier to classify a set of objects into multiple classes, wherein the set of objects comprise textual objects including a word or a sentence;

applying a plurality of binary classifiers to the set of objects, wherein the plurality of binary classifiers are decomposed from the multi-class classifier, each binary classifier classifying the set of the objects into a first group consisting of one or more classes selected from the multiple classes and a second group consisting of one or more remaining classes of the multiple classes; and

jointly classifying the set of objects using the multi-class classifier and the plurality of binary classifiers.

12. The method of claim 11 , comprising:

jointly training the multi-class classifier and the plurality of binary classifiers by minimizing a joint loss comprising a multi-class classification loss corresponding to the multi-class classifier and one or more binary classification losses corresponding to one or more binary classifiers selected from the plurality of binary classifiers.

13. The method of claim 11 , comprising:

receiving, by an encoder corresponding to at least one binary classifier, the set of objects; and

generating, by the encoder, contextual information from the set of the objects.

14. The method of claim 13 , further comprising:

determining, by a private attention layer corresponding to the at least one binary classifier, class-specific information based on the contextual information; and

determining, by a shared attention layer, class-agnostic information based on the contextual information.

15. The method of claim 14 , wherein the class-agnostic information comprises a shared feature shared by multiple classes.

16. The method of claim 14 , further comprising:

refining, by a discriminator, the class-agnostic information by minimizing the adversarial loss.

17. The method of claim 16 , further comprising:

jointly training the multi-class classifier and the plurality of binary classifiers by minimizing a joint loss comprising:

a multi-class classification loss corresponding to the multi-class classifier;

one or more binary classification losses corresponding to one or more binary classifiers selected from the plurality of binary classifiers; and

the adversarial loss.

18. The method of claim 14 , further comprising:

generating classification features of the at least one binary classifier by concatenating the class-specific information and the class-agnostic information.

19. The method of claim 14 , further comprising:

generating classification features of the multi-class classifier by concatenating class-specific information corresponding to multiple binary classifiers and the class-agnostic information.

20. A non-transitory computer-readable medium having instructions stored thereon that, when executed by at least one processor, causes the processor to perform a method for classifying a set of objects, the method comprising:

training a multi-class classifier based on calculating a shared representation and an adversarial loss;

applying the multi-class classifier to classify the set of objects into multiple classes, wherein the set of objects comprise textual objects including a word or a sentence;

applying a plurality of binary classifiers to the set of objects, wherein the plurality of binary classifiers are decomposed from the multi-class classifier, each binary classifier classifying the set of the objects into a first group consisting of one or more classes selected from the multiple classes and a second group consisting of one or more remaining classes of the multiple classes; and

jointly classifying the set of objects using the multi-class classifier and the plurality of binary classifiers.