US 11,983,492 B2
Adversarial multi-binary neural network for multi-class classification
Kun Han, Mountain View, CA (US); and Haiyang Xu, Beijing (CN)
Assigned to BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD., Beijing (CN)
Filed by BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD., Beijing (CN)
Filed on Sep. 8, 2020, as Appl. No. 17/014,256.
Application 17/014,256 is a continuation of application No. PCT/CN2019/087032, filed on May 15, 2019.
Prior Publication US 2020/0401844 A1, Dec. 24, 2020
Int. Cl. G06F 40/216 (2020.01); G06F 18/211 (2023.01); G06F 18/2132 (2023.01); G06F 18/2431 (2023.01); G06N 3/044 (2023.01); G06N 20/20 (2019.01); G06N 3/045 (2023.01)
CPC G06F 40/216 (2020.01) [G06F 18/211 (2023.01); G06F 18/2132 (2023.01); G06F 18/2431 (2023.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 20/20 (2019.01)] 20 Claims
OG exemplary drawing
 
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.