R Wu, C Guo, Y Su… - Advances in Neural …, 2021 - proceedings.neurips.cc
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 …
J Kremer, F Sha, C Igel - International conference on artificial …, 2018 - proceedings.mlr.press
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 …
D Yu, W Shi, Q Yu - Advances in Neural Information …, 2024 - proceedings.neurips.cc
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 …
B Han, IW Tsang, L Chen, PY Celina… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
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 …