When can unlabeled data improve the learning rate?

by   Christina Göpfert, et al.

In semi-supervised classification, one is given access both to labeled and unlabeled data. As unlabeled data is typically cheaper to acquire than labeled data, this setup becomes advantageous as soon as one can exploit the unlabeled data in order to produce a better classifier than with labeled data alone. However, the conditions under which such an improvement is possible are not fully understood yet. Our analysis focuses on improvements in the minimax learning rate in terms of the number of labeled examples (with the number of unlabeled examples being allowed to depend on the number of labeled ones). We argue that for such improvements to be realistic and indisputable, certain specific conditions should be satisfied and previous analyses have failed to meet those conditions. We then demonstrate examples where these conditions can be met, in particular showing rate changes from 1/√(ℓ) to e^-cℓ and from 1/√(ℓ) to 1/ℓ. These results improve our understanding of what is and isn't possible in semi-supervised learning.


page 1

page 2

page 3

page 4


Semi-Supervised Learning: the Case When Unlabeled Data is Equally Useful

Semi-supervised learning algorithms attempt to take advantage of relativ...

Unlabeled Data Help: Minimax Analysis and Adversarial Robustness

The recent proposed self-supervised learning (SSL) approaches successful...

Can I Trust My Fairness Metric? Assessing Fairness with Unlabeled Data and Bayesian Inference

We investigate the problem of reliably assessing group fairness when lab...

Learning by Association - A versatile semi-supervised training method for neural networks

In many real-world scenarios, labeled data for a specific machine learni...

Reference Distance Estimator

A theoretical study is presented for a simple linear classifier called r...

Semi-Supervised Learning for Detecting Human Trafficking

Human trafficking is one of the most atrocious crimes and among the chal...

Hierarchical Classification of Enzyme Promiscuity Using Positive, Unlabeled, and Hard Negative Examples

Despite significant progress in sequencing technology, there are many ce...

Please sign up or login with your details

Forgot password? Click here to reset