Semi-Supervised Laplacian Learning on Stiefel Manifolds

by   Chester Holtz, et al.

Motivated by the need to address the degeneracy of canonical Laplace learning algorithms in low label rates, we propose to reformulate graph-based semi-supervised learning as a nonconvex generalization of a Trust-Region Subproblem (TRS). This reformulation is motivated by the well-posedness of Laplacian eigenvectors in the limit of infinite unlabeled data. To solve this problem, we first show that a first-order condition implies the solution of a manifold alignment problem and that solutions to the classical Orthogonal Procrustes problem can be used to efficiently find good classifiers that are amenable to further refinement. Next, we address the criticality of selecting supervised samples at low-label rates. We characterize informative samples with a novel measure of centrality derived from the principal eigenvectors of a certain submatrix of the graph Laplacian. We demonstrate that our framework achieves lower classification error compared to recent state-of-the-art and classical semi-supervised learning methods at extremely low, medium, and high label rates. Our code is available on github[anonymized for submission].


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

We propose a new framework, called Poisson learning, for graph based sem...

Properly-weighted graph Laplacian for semi-supervised learning

The performance of traditional graph Laplacian methods for semi-supervis...

Graph Based Semi-supervised Learning Using Spatial Segregation Theory

In this work we address graph based semi-supervised learning using the t...

Posterior Contraction Rates for Graph-Based Semi-Supervised Classification

This paper studies Bayesian nonparametric estimation of a binary regress...

Large Data and Zero Noise Limits of Graph-Based Semi-Supervised Learning Algorithms

Scalings in which the graph Laplacian approaches a differential operator...

Generalized Label Propagation Methods for Semi-Supervised Learning

The key challenge in semi-supervised learning is how to effectively leve...

Incremental Spectral Sparsification for Large-Scale Graph-Based Semi-Supervised Learning

While the harmonic function solution performs well in many semi-supervis...

Please sign up or login with your details

Forgot password? Click here to reset