# More Than Meets The Eye: Semi-supervised Learning Under Non-IID Data

arXiv: https://arxiv.org/abs/2104.10223 · HTML: https://mlsanity.com/paper/2104.10223/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 20 Apr 2021.

## Builds on (most cited first, 10 of 10)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [The Effectiveness of Data Augmentation in Image Classification using Deep Learning](https://mlsanity.com/paper/1712.04621/) (2017)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay](https://mlsanity.com/paper/1803.09820/) (2018)
- [Characterizing Concept Drift](https://mlsanity.com/paper/1511.03816/) (2015)
- [Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2007.07695/) (2020)

## Built on by (most cited first, 2 of 2)

- [A Real Use Case of Semi-Supervised Learning for Mammogram Classification in a Local Clinic of Costa Rica](https://mlsanity.com/paper/2107.11696/) (2021)
- [Dealing with Distribution Mismatch in Semi-supervised Deep Learning for Covid-19 Detection Using Chest X-ray Images: A Novel Approach Using Feature Densities](https://mlsanity.com/paper/2109.00889/) (2021)

## Abstract (arXiv)

A common heuristic in semi-supervised deep learning (SSDL) is to select unlabelled data based on a notion of semantic similarity to the labelled data. For example, labelled images of numbers should be paired with unlabelled images of numbers instead of, say, unlabelled images of cars. We refer to this practice as semantic data set matching. In this work, we demonstrate the limits of semantic data set matching. We show that it can sometimes even degrade the performance for a state of the art SSDL algorithm. We present and make available a comprehensive simulation sandbox, called non-IID-SSDL, for stress testing an SSDL algorithm under different degrees of distribution mismatch between the labelled and unlabelled data sets. In addition, we demonstrate that simple density based dissimilarity measures in the feature space of a generic classifier offer a promising and more reliable quantitative matching criterion to select unlabelled data before SSDL training.