We study the problem of learning classifiers that perform well across (known or unknown)
groups of data. After observing that common worst-group-accuracy datasets suffer from …

The paradigm of worst-group loss minimization has shown its promise in avoiding to learn
spurious correlations, but requires costly additional supervision on spurious attributes. To …

Neural networks are prone to be biased towards spurious correlations between classes and
latent attributes exhibited in a major portion of training data, which ruins their generalization …

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 …

Machine learning (ML) is increasingly being used to make decisions in our society. ML
models, however, can be unfair to certain demographic groups (eg, African Americans or …

Recent research suggests that predictions made by machine-learning models can amplify
biases present in the training data. When a model amplifies bias, it makes certain …

Overparameterized neural networks can be highly accurate on average on an iid test set yet
consistently fail on atypical groups of the data (eg, by learning spurious correlations that …

Classifiers can be trained with data-dependent constraints to satisfy fairness goals, reduce
churn, achieve a targeted false positive rate, or other policy goals. We study the …

We propose simple active sampling and reweighting strategies for optimizing min-max
fairness that can be applied to any classification or regression model learned via loss …

Real-world datasets exhibit imbalances of varying types and degrees. Several techniques
based on re-weighting and margin adjustment of loss are often used to enhance the …