English

Unlabeled Data Help in Graph-Based Semi-Supervised Learning: A Bayesian Nonparametrics Perspective

Statistics Theory 2021-06-15 v3 Machine Learning Statistics Theory

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-23T18:07:40.340Z