Semi-supervised regression with skewed data via adversarially forcing the distribution of predicted values

no code implementations • 1 Jan 2021 • Dae-Woong Jeong, Kiyoung Kim, ChangYoung Park, Sehui Han, Woohyung Lim

We assume the existence of enough unlabeled data that follow the true distribution, and that the true distribution can be roughly estimated from domain knowledge or a few samples.

Drug Discovery regression