# Negative sampling in semi-supervised learning

arXiv: https://arxiv.org/abs/1911.05166 · HTML: https://mlsanity.com/paper/1911.05166/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2019.

## Built on by (most cited first, 11 of 11)

- [Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data](https://mlsanity.com/paper/2303.11066/) (2023)
- [Rethinking Precision of Pseudo Label: Test-Time Adaptation via Complementary Learning](https://mlsanity.com/paper/2301.06013/) (2023)
- [Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical](https://mlsanity.com/paper/2311.15502/) (2023)
- [Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning](https://mlsanity.com/paper/2508.00716/) (2025)
- [MaxMatch: Semi-Supervised Learning with Worst-Case Consistency](https://mlsanity.com/paper/2209.12611/) (2022)
- [Semi-supervised Object Detection via Virtual Category Learning](https://mlsanity.com/paper/2207.03433/) (2022)
- [Fast FixMatch: Faster Semi-Supervised Learning with Curriculum Batch Size](https://mlsanity.com/paper/2309.03469/) (2023)
- [Taming Overconfident Prediction on Unlabeled Data from Hindsight](https://mlsanity.com/paper/2112.08200/) (2021)
- [One-bit Supervision for Image Classification: Problem, Solution, and Beyond](https://mlsanity.com/paper/2311.15225/) (2023)
- [SemAlign: Language Guided Semi-supervised Domain Generalization](https://mlsanity.com/paper/2601.11724/) (2026)
- [Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions](https://mlsanity.com/paper/2608.06896/) (2026)

## Abstract (arXiv)

We introduce Negative Sampling in Semi-Supervised Learning (NS3L), a simple, fast, easy to tune algorithm for semi-supervised learning (SSL). NS3L is motivated by the success of negative sampling/contrastive estimation. We demonstrate that adding the NS3L loss to state-of-the-art SSL algorithms, such as the Virtual Adversarial Training (VAT), significantly improves upon vanilla VAT and its variant, VAT with Entropy Minimization. By adding the NS3L loss to MixMatch, the current state-of-the-art approach on semi-supervised tasks, we observe significant improvements over vanilla MixMatch. We conduct extensive experiments on the CIFAR10, CIFAR100, SVHN and STL10 benchmark datasets.