# Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

arXiv: https://arxiv.org/abs/1804.09170 · HTML: https://mlsanity.com/paper/1804.09170/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2018.

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

- [Detecting and Learning Out-of-Distribution Data in the Open world: Algorithm and Theory](https://mlsanity.com/paper/2310.06221/) (2023)
- [On Training Implicit Meta-Learning With Applications to Inductive Weighing in Consistency Regularization](https://mlsanity.com/paper/2310.18741/) (2023)
- [InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning](https://mlsanity.com/paper/2403.10658/) (2024)
- [Exploring Probabilistic Models for Semi-supervised Learning](https://mlsanity.com/paper/2404.04199/) (2024)

## Abstract (arXiv)

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that these algorithms would face in real-world applications. After creating a unified reimplementation of various widely-used SSL techniques, we test them in a suite of experiments designed to address these issues. We find that the performance of simple baselines which do not use unlabeled data is often underreported, that SSL methods differ in sensitivity to the amount of labeled and unlabeled data, and that performance can degrade substantially when the unlabeled dataset contains out-of-class examples. To help guide SSL research towards real-world applicability, we make our unified reimplemention and evaluation platform publicly available.