Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because
models can easily overfit them. There are many types of label noise, such as symmetric …

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 …

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language
Models (PLMs) have achieved substantial advancements in the field of natural language …

This paper explains the generalization power of a deep neural network (DNN) from the
perspective of interactions. Although there is no universally-accepted definition of the …

Recently, a novel generative retrieval (GR) paradigm has been proposed, where a single
sequence-to-sequence model is learned to directly generate a list of relevant document …

The sample selection approach is very popular in learning with noisy labels. As deep
networks “learn pattern first”, prior methods built on sample selection share a similar training …

Learning from noisy labels (LNL) is a challenge that arises in many real-world scenarios
where collected training data can contain incorrect or corrupted labels. Most existing …

Learning from noisy labels is a challenge that arises in many real-world applications where
training data can contain incorrect or corrupted labels. When fine-tuning language models …

Characterizing samples that are difficult to learn from is crucial to developing highly
performant ML models. This has led to numerous Hardness Characterization Methods …

As an inevitable issue in annotating large-scale datasets, instance-dependent label noise
(IDN) can cause serious overfitting in neural networks. To combat IDN, label reconstruction …