The digital world is generating data at a staggering and still increasing rate. While these “big
data” have unlocked novel opportunities to understand public health, they hold still greater …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Deep learning with noisy labels is practically challenging, as the capacity of deep models is
so high that they can totally memorize these noisy labels sooner or later during training …

Recent deep networks are capable of memorizing the entire data even when the labels are
completely random. To overcome the overfitting on corrupted labels, we propose a novel …

We present a theoretically grounded approach to train deep neural networks, including
recurrent networks, subject to class-dependent label noise. We propose two procedures for …

Learning with noisy labels is one of the hottest problems in weakly-supervised learning.
Based on memorization effects of deep neural networks, training on small-loss instances …

Deep Learning with noisy labels is a practically challenging problem in weakly-supervised
learning. The state-of-the-art approaches" Decoupling" and" Co-teaching+" claim that the" …

Identifying pathogenic variants and underlying functional alterations is challenging. To this
end, we introduce MutPred2, a tool that improves the prioritization of pathogenic amino acid …

From only positive (P) and unlabeled (U) data, a binary classifier could be trained with PU
learning, in which the state of the art is unbiased PU learning. However, if its model is very …

In label-noise learning, the noise transition matrix, bridging the class posterior for noisy and
clean data, has been widely exploited to learn statistically consistent classifiers. The …