# Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model

arXiv: https://arxiv.org/abs/2503.00884 · HTML: https://mlsanity.com/paper/2503.00884/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Interpolation Consistency Training for Semi-Supervised Learning](https://mlsanity.com/paper/1903.03825/) (2019)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning](https://mlsanity.com/paper/2301.10921/) (2023)
- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [Multi-Task Curriculum Framework for Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2007.11330/) (2020)
- [IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization](https://mlsanity.com/paper/2308.13168/) (2023)
- [A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2311.03524/) (2023)
- [FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning](https://mlsanity.com/paper/2310.16412/) (2023)
- [Imbalanced Semi-supervised Learning with Bias Adaptive Classifier](https://mlsanity.com/paper/2207.13856/) (2022)
- [Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning](https://mlsanity.com/paper/2308.06777/) (2023)
- [Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data](https://mlsanity.com/paper/2208.11870/) (2022)
- [Robust Semi-Supervised Learning in Open Environments](https://mlsanity.com/paper/2412.18256/) (2024)
- [Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning](https://mlsanity.com/paper/2305.18158/) (2023)

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

- [USE: Uncertainty Structure Estimation for Robust Semi-Supervised Learning](https://mlsanity.com/paper/2603.00404/) (2026)
- [Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning](https://mlsanity.com/paper/2605.23595/) (2026)
- [C-Score: Beyond Accuracy for Robustness Assessment in Semi-Supervised Learning under Open-World Unlabeled Contamination](https://mlsanity.com/paper/2608.20667/) (2026)

## Abstract (arXiv)

Semi-supervised learning (SSL) effectively leverages unlabeled data and has been proven successful across various fields. Current safe SSL methods believe that unseen classes in unlabeled data harm the performance of SSL models. However, previous methods for assessing the impact of unseen classes on SSL model performance are flawed. They fix the size of the unlabeled dataset and adjust the proportion of unseen classes within the unlabeled data to assess the impact. This process contravenes the principle of controlling variables. Adjusting the proportion of unseen classes in unlabeled data alters the proportion of seen classes, meaning the decreased classification performance of seen classes may not be due to an increase in unseen class samples in the unlabeled data, but rather a decrease in seen class samples. Thus, the prior flawed assessment standard that ``unseen classes in unlabeled data can damage SSL model performance" may not always hold true. This paper strictly adheres to the principle of controlling variables, maintaining the proportion of seen classes in unlabeled data while only changing the unseen classes across five critical dimensions, to investigate their impact on SSL models from global robustness and local robustness. Experiments demonstrate that unseen classes in unlabeled data do not necessarily impair the performance of SSL models; in fact, under certain conditions, unseen classes may even enhance them.