Jpmorgan Chase Bank, N.a.

Wei-Cheng Huang

Richard Chen

Zhonghao Shi

Hsiang Hsu

A method may include: receiving an original dataset and a sensitive attribute; initializing a distilled dataset from the original dataset; initializing a classification model; sampling original dataset data and an original dataset label from the original dataset, and distilled dataset data and a distilled dataset label from the distilled dataset; providing the sampled original dataset data from the original dataset to the classification model, resulting in an original dataset prediction probability; providing the sampled distilled dataset data from the distilled dataset to the classification model, resulting in a distilled dataset prediction probability; calculating a distilled dataset cross-entropy loss for the distilled dataset prediction probability and the distilled dataset label; calculating distilled dataset gradients for the distilled dataset cross-entropy loss; calculating a distance between the gradients as a matching loss; and updating the distilled dataset with the matching loss.

Growing community of inventors

New York, NY, United States of America

Wei-Cheng Huang