Predict Responsibly: Increasing Fairness by Learning To Defer

Machine learning systems, which are often used for high-stakes decisions, suffer from two mutually reinforcing problems: unfairness and opaqueness. Many popular models, although generally accurate, cannot express uncertainty about their predictions. Even in regimes where a model is inaccurate, users may trust the model’s predictions too fully, and allow its biases to reinforce the user’s own. In this work, we explore models that learn to defer. In our scheme, a model learns to classify accurately and fairly, but also to defer if necessary, passing judgment to a downstream decision-maker such as a human user. We further propose a learning algorithm which accounts for potential biases held by decision-makers later in a pipeline. Experiments on real-world datasets demonstrate that learning to defer can make a model not only more accurate but also less biased. Even when operated by highly biased users, we show that deferring models can still greatly improve the fairness of the entire pipeline.