# An Uncertainty-Aware Pseudo-Label Selection Framework using Regularized Conformal Prediction

arXiv: https://arxiv.org/abs/2309.15963 · HTML: https://mlsanity.com/paper/2309.15963/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 5 references that are in the map.
- First posted on arXiv 30 Aug 2023.

## Builds on (most cited first, 4 of 4)

- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification](https://mlsanity.com/paper/2107.07511/) (2021)
- [Uncertainty Sets for Image Classifiers using Conformal Prediction](https://mlsanity.com/paper/2009.14193/) (2020)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)

## Built on by (most cited first, 1 of 1)

- [ESRVS: Extreme Semi-Supervised Retinal Vessel Segmentation with a Single Annotated Image](https://mlsanity.com/paper/2607.24453/) (2026)

## Abstract (arXiv)

Consistency regularization-based methods are prevalent in semi-supervised learning (SSL) algorithms due to their exceptional performance. However, they mainly depend on domain-specific data augmentations, which are not usable in domains where data augmentations are less practicable. On the other hand, Pseudo-labeling (PL) is a general and domain-agnostic SSL approach that, unlike consistency regularization-based methods, does not rely on the domain. PL underperforms due to the erroneous high-confidence predictions from poorly calibrated models. This paper proposes an uncertainty-aware pseudo-label selection framework that employs uncertainty sets yielded by the conformal regularization algorithm to fix the poor calibration neural networks, reducing noisy training data. The codes of this work are available at: https://github.com/matinmoezzi/ups conformal classification