Publication | International Conference on Machine Learning 2014

Wasserstein propagation for semi-supervised learning

Abstract

Wasserstein propagation for semi-supervised learning

J. Solomon, R. Rustamov, L. Guibas, Adrian Butscher

International Conference on Machine Learning 2014

Probability distributions and histograms are natural representations for product ratings, traffic measurements, and other data considered in many machine learning applications. Thus, this paper introduces a technique for graph-based semi-supervised learning of histograms, derived from the theory of optimal transportation. Our method has several properties making it suitable for this application; in particular, its behavior can be characterized by the moments and shapes of the histograms at the labeled nodes. In addition, it can be used for histograms on non-standard domains like circles, revealing a strategy for manifold-valued semi-supervised learning. We also extend this technique to related problems such as smoothing distributions on graph nodes.

Download publication

Associated Autodesk Researchers

Justin Solomon

Stanford University

Raif Rustamov

Stanford University

Leonidas Guibas

Stanford University

View all researchers

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us