Differentiable Clustering with Perturbed Spanning Forests

Lawrence Stewart, Francis Bach, Felipe Llinares-López, Quentin Berthet

Keywords: Structured learning, Clustering, Differentiable, weakly supervised, semi-supervised, representation learning

TL;DR: A method for differentiable clustering and techniques to learn from clustering data, end-to-end.

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: 8103