Neural networks trained with ERM (empirical risk minimization) sometimes learn unintended
decision rules, in particular when their training data is biased, ie, when training labels are …

Many datasets are biased, namely they contain easy-to-learn features that are highly
correlated with the target class only in the dataset but not in the true underlying distribution …

Datasets for training machine learning models tend to be biased unless the data is collected
with complete care. In such a biased dataset, models are susceptible to making predictions …

Neural networks often learn to make predictions that overly rely on spurious corre-lation
existing in the dataset, which causes the model to be biased. While previous work tackles …

Mixup, which creates synthetic training instances by linearly interpolating random sample
pairs, is a simple and yet effective regularization technique to boost the performance of deep …

Deep neural networks have been shown to be very powerful modeling tools for many
supervised learning tasks involving complex input patterns. However, they can also easily …

Many machine learning algorithms are trained and evaluated by splitting data from a single
source into training and test sets. While such focus on in-distribution learning scenarios has …

Despite the impressive prediction ability, machine learning models show discrimination
towards certain demographics and suffer from unfair prediction behaviors. To alleviate the …

Contrastive learning has recently emerged as a promising approach for learning data
representations that discover and disentangle the explanatory factors of the data. Previous …

Classifiers are biased when trained on biased datasets. As a remedy, we propose Learning
to Split (ls), an algorithm for automatic bias detection. Given a dataset with input-label pairs …