Differentiable Clustering and Partial Fenchel-Young Losses
Keywords: clustering, differentiable, differentiable clustering, perturbations, perturbed optimizers, spanning trees, spanning forests, fenchel, young, fenchel-young
TL;DR: We introduce a differentiable clustering method based on stochastic perturbations of minimum-weight spanning forests
Abstract: We introduce a differentiable clustering method based on stochastic perturbations of minimum-weight spanning forests. This allows us to include clustering in end-to-end trainable pipelines, with efficient gradients. We show that our method performs well even in difficult settings, such as data sets with high noise and challenging geometries. We also formulate an ad hoc loss to efficiently learn from partial clustering data using this operation. We demonstrate its performance on several data sets for supervised and semi-supervised tasks.
Submission Number: 62