Abstract Machine learning models have been found to learn shortcuts---unintended decision
rules that are unable to generalize---undermining models' reliability. Previous works address …

In this work, we consider the problem of intersectional group fairness in the classification
setting, where the objective is to learn discrimination-free models in the presence of several …

With the advent of machine learning, the government institutions and other bureaucracy are
undergoing a paradigm shift, as algorithms increasingly assist in and even replace some of …

While many AI applications make human life more convenient, they also bring concerns and
worries to human societies. For example, self-driving cars may become dangerous under …