Generating Unobserved Alternatives
This addresses a gap in machine learning for tasks with multiple valid answers but limited supervision, offering a novel solution for applications like creative generation or ambiguous decision-making.
The paper tackles the problem of generating multiple correct predictions when only one is provided as supervision, developing an approach that produces diverse high-quality outputs different from the observed one.
We consider problems where multiple predictions can be considered correct, but only one of them is given as supervision. This setting differs from both the regression and class-conditional generative modelling settings: in the former, there is a unique observed output for each input, which is provided as supervision; in the latter, there are many observed outputs for each input, and many are provided as supervision. Applying either regression methods and conditional generative models to the present setting often results in a model that can only make a single prediction for each input. We explore several problems that have this property and develop an approach that can generate multiple high-quality predictions given the same input. As a result, it can be used to generate high-quality outputs that are different from the observed output.