Learning with noisy labels (LNL) aims to ensure model generalization given a label-
corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine …

In the presence of noisy labels, designing robust loss functions is critical for securing the
generalization performance of deep neural networks. Cross Entropy (CE) loss has been …

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 …

The rawly collected training data often comes with separate noisy labels collected from
multiple imperfect annotators (eg, via crowdsourcing). A typical way of using these separate …

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 …

Pre-training on large-scale datasets and then fine-tuning on downstream tasks have
become a standard practice in deep learning. However, pre-training data often contain label …

Foundation models are usually pre-trained on large-scale datasets and then adapted to
downstream tasks through tuning. However, the large-scale pre-training datasets, often …

Deep neural networks (DNNs) involve advanced image processing but depend on large
quantities of high-quality labeled data. The presence of noisy data significantly degrades the …

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 …

Label noise commonly found in real-world datasets has a detrimental impact on a model's
generalization. To effectively detect incorrectly labeled instances previous works have …