Federated Learning (FL) heavily depends on label quality for its performance. However, the
label distribution among individual clients is always both noisy and heterogeneous. The …

Language models have shown promise in various tasks but can be affected by undesired
data during training, fine-tuning, or alignment. For example, if some unsafe conversations …

Learning with reduced labeling standards, such as noisy label, partial label, and
supplementary unlabeled data, which we generically refer to as imprecise label, is a …

Evaluating fairness can be challenging in practice because the sensitive attributes of data
are often inaccessible due to privacy constraints. The go-to approach that the industry …

Learning from crowds describes that the annotations of training data are obtained with
crowd-sourcing services. Multiple annotators each complete their own small part of the …

Designing robust loss functions is popular in learning with noisy labels while existing
designs did not explicitly consider the overfitting property of deep neural networks (DNNs) …