In this paper we analyze the graph-based approach to semi-supervised learning under a manifold assumption. We adopt a Bayesian perspective and demonstrate that, for a suitable choice of prior constructed with sufficiently many unlabeled data, the posterior contracts around the truth at a rate that is minimax optimal up to a logarithmic factor. Our theory covers both regression and classification.
@article{arxiv.2008.11809,
title = {Unlabeled Data Help in Graph-Based Semi-Supervised Learning: A Bayesian Nonparametrics Perspective},
author = {Daniel Sanz-Alonso and Ruiyi Yang},
journal= {arXiv preprint arXiv:2008.11809},
year = {2021}
}