# Learning to Impute: A General Framework for Semi-supervised Learning

arXiv: https://arxiv.org/abs/1912.10364 · HTML: https://mlsanity.com/paper/1912.10364/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2019.

## Built on by (most cited first, 3 of 3)

- [Meta-Calibration: Learning of Model Calibration Using Differentiable Expected Calibration Error](https://mlsanity.com/paper/2106.09613/) (2021)
- [Learning to Annotate Part Segmentation with Gradient Matching](https://mlsanity.com/paper/2211.03003/) (2022)
- [Built Year Prediction from Buddha Face with Heterogeneous Labels](https://mlsanity.com/paper/2109.00812/) (2021)

## Abstract (arXiv)

Recent semi-supervised learning methods have shown to achieve comparable results to their supervised counterparts while using only a small portion of labels in image classification tasks thanks to their regularization strategies. In this paper, we take a more direct approach for semi-supervised learning and propose learning to impute the labels of unlabeled samples such that a network achieves better generalization when it is trained on these labels. We pose the problem in a learning-to-learn formulation which can easily be incorporated to the state-of-the-art semi-supervised techniques and boost their performance especially when the labels are limited. We demonstrate that our method is applicable to both classification and regression problems including image classification and facial landmark detection tasks.