US 11,816,183 B2
Methods and systems for mining minority-class data samples for training a neural network
Gursimran Singh, Delta (CA); Lingyang Chu, Burnaby (CA); Lanjun Wang, Toronto (CA); and Yong Zhang, Richmond (CA)
Assigned to HUAWEI CLOUD COMPUTING TECHNOLOGIES CO., LTD., Gui'an New District (CN)
Filed by HUAWEI CLOUD COMPUTING TECHNOLOGIES CO., LTD., Gui'an New District (CN)
Filed on Dec. 11, 2020, as Appl. No. 17/119,989.
Prior Publication US 2022/0188568 A1, Jun. 16, 2022
Int. Cl. G06N 3/08 (2023.01); G06F 18/214 (2023.01); G06N 3/084 (2023.01); G06N 3/045 (2023.01)
CPC G06F 18/2148 (2023.01) [G06F 18/2155 (2023.01); G06N 3/045 (2023.01); G06N 3/084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for identifying a candidate minority-class data sample, the method comprising:
receiving an activation comprising values of an inner-layer activation representing a given data sample, the received activation being generated by a client neural network that has been trained to perform a classification;
forward propagating the received activation through a trained recalibration neural network, to generate a recalibrated activation, wherein the trained recalibration neural network has been trained to perform the classification in a manner to avoid overtraining;
forward propagating the recalibrated activation through a trained anomaly detector, wherein the trained anomaly detector has been trained on activations in which majority-class data samples form a majority;
computing a minority-class score for the received activation, based on an anomaly detector output;
identifying the given data sample as a candidate minority-class data sample, based on a comparison of the minority-class score against a minority-class threshold; and
communicating an identification of the given data sample as the candidate minority-class data sample.