Weakly Supervised Clustering: Learning Fine-Grained Signals from Coarse Side Information

Consider a classification problem where we do not have access to labels for individual training examples, but only have average labels over sub-populations. We give practical examples of this setup, and show how these classification tasks can usefully be analyzed as weakly supervised clustering problems. We propose three approaches to solving the weakly supervised clustering problem, including a latent variables model that performs well in our experiments. We illustrate our methods on an industry dataset that was the original motivation for this research.