# SaaS: Speed as a Supervisor for Semi-supervised Learning

arXiv: https://arxiv.org/abs/1805.00980 · HTML: https://mlsanity.com/paper/1805.00980/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2018.

## Built on by (most cited first, 4 of 4)

- [Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels](https://mlsanity.com/paper/2103.13646/) (2021)
- [Semi-supervised Deep Learning for Image Classification with Distribution Mismatch: A Survey](https://mlsanity.com/paper/2203.00190/) (2022)
- [Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densities](https://mlsanity.com/paper/2109.00889/) (2021)
- [Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound](https://mlsanity.com/paper/2203.06639/) (2022)

## Abstract (arXiv)

We introduce the SaaS Algorithm for semi-supervised learning, which uses learning speed during stochastic gradient descent in a deep neural network to measure the quality of an iterative estimate of the posterior probability of unknown labels. Training speed in supervised learning correlates strongly with the percentage of correct labels, so we use it as an inference criterion for the unknown labels, without attempting to infer the model parameters at first. Despite its simplicity, SaaS achieves state-of-the-art results in semi-supervised learning benchmarks.