# Semi-Supervised Learning by Label Gradient Alignment

arXiv: https://arxiv.org/abs/1902.02336 · HTML: https://mlsanity.com/paper/1902.02336/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2019.

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

- [Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples](https://mlsanity.com/paper/2104.13963/) (2021)
- [AutoDropout: Learning Dropout Patterns to Regularize Deep Networks](https://mlsanity.com/paper/2101.01761/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Knowledge Distillation with Adapted Weight](https://mlsanity.com/paper/2501.02705/) (2025)

## Abstract (arXiv)

We present label gradient alignment, a novel algorithm for semi-supervised learning which imputes labels for the unlabeled data and trains on the imputed labels. We define a semantically meaningful distance metric on the input space by mapping a point (x, y) to the gradient of the model at (x, y). We then formulate an optimization problem whose objective is to minimize the distance between the labeled and the unlabeled data in this space, and we solve it by gradient descent on the imputed labels. We evaluate label gradient alignment using the standardized architecture introduced by Oliver et al. (2018) and demonstrate state-of-the-art accuracy in semi-supervised CIFAR-10 classification.