The standard supervised learning paradigm works effectively when training data shares the
same distribution as the upcoming testing samples. However, this stationary assumption is …

Abstract Machine learning models often encounter distribution shifts when deployed in the
real world. In this paper, we focus on adaptation to label distribution shift in the online …

This paper focuses on supervised and unsupervised online label shift, where the class
marginals $ Q (y) $ variesbut the class-conditionals $ Q (x| y) $ remain invariant. In the …

In many real-world applications, data are continuously accumulated within open
environments. For instance, in disease diagnosis, the prevalence of diseases can vary …

Active label correction addresses the problem of learning from input data for which noisy
labels are available (eg, from imprecise measurements or crowd-sourcing) and each true …

The label shift problem refers to the supervised learning setting where the train and test
label distributions do not match. Existing work addressing label shift usually assumes …

In active learning (AL), we focus on reducing the data annotation cost from the model
training perspective. However," testing'', which often refers to the model evaluation process …

We study a robust alternative to empirical risk minimization called distributionally robust
learning (DRL), in which one learns to perform against an adversary who can choose the …

Despite the large progress in supervised learning with neural networks, there are significant
challenges in obtaining high-quality, large-scale and accurately labelled datasets. In such a …

Large-scale learning problems require a plethora of labels that can be efficiently collected
from crowdsourcing services at low cost. However, labels annotated by crowdsourced …