Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates

arXiv2006.11184MaRDI QIDQ6343287

Author name not available (Why is that?)

Publication date: 19 June 2020

Abstract: We propose a new framework, called Poisson learning, for graph based semi-supervised learning at very low label rates. Poisson learning is motivated by the need to address the degeneracy of Laplacian semi-supervised learning in this regime. The method replaces the assignment of label values at training points with the placement of sources and sinks, and solves the resulting Poisson equation on the graph. The outcomes are provably more stable and informative than those of Laplacian learning. Poisson learning is efficient and simple to implement, and we present numerical experiments showing the method is superior to other recent approaches to semi-supervised learning at low label rates on MNIST, FashionMNIST, and Cifar-10. We also propose a graph-cut enhancement of Poisson learning, called Poisson MBO, that gives higher accuracy and can incorporate prior knowledge of relative class sizes.

Has companion code repository: https://github.com/jwcalder/GraphLearning

Mathematics Subject Classification ID

No records found.

This page was built for publication: Poisson Learning: Graph Based Semi-Supervised Learning At Very Low Label Rates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6343287)