Learning Representations by Humans, for Humans
This work addresses the challenge of enhancing human decision-making in AI-assisted systems, offering a novel approach that is not incremental but shifts the paradigm from prediction to representation.
The paper tackles the problem of improving human decision-making by reframing problems with human-facing representations, rather than focusing on machine prediction accuracy, and demonstrates successful application across various tasks.
When machine predictors can achieve higher performance than the human decision-makers they support, improving the performance of human decision-makers is often conflated with improving machine accuracy. Here we propose a framework to directly support human decision-making, in which the role of machines is to reframe problems rather than to prescribe actions through prediction. Inspired by the success of representation learning in improving performance of machine predictors, our framework learns human-facing representations optimized for human performance. This "Mind Composed with Machine" framework incorporates a human decision-making model directly into the representation learning paradigm and is trained with a novel human-in-the-loop training procedure. We empirically demonstrate the successful application of the framework to various tasks and representational forms.