# MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization

arXiv: https://arxiv.org/abs/2012.00150 · HTML: https://mlsanity.com/paper/2012.00150/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

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

- [Partner-Assisted Learning for Few-Shot Image Classification](https://mlsanity.com/paper/2109.07607/) (2021)
- [LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification](https://mlsanity.com/paper/2106.04527/) (2021)
- [Risk Bounds for Learning via Hilbert Coresets](https://mlsanity.com/paper/2103.15569/) (2021)
- [Deep Dive into Semi-Supervised ELBO for Improving Classification Performance](https://mlsanity.com/paper/2108.12734/) (2021)

## Abstract (arXiv)

Deep neural networks are powerful, massively parameterized machine learning models that have been shown to perform well in supervised learning tasks. However, very large amounts of labeled data are usually needed to train deep neural networks. Several semi-supervised learning approaches have been proposed to train neural networks using smaller amounts of labeled data with a large amount of unlabeled data. The performance of these semi-supervised methods significantly degrades as the size of labeled data decreases. We introduce Mutual-information-based Unsupervised & Semi-supervised Concurrent LEarning (MUSCLE), a hybrid learning approach that uses mutual information to combine both unsupervised and semi-supervised learning. MUSCLE can be used as a stand-alone training scheme for neural networks, and can also be incorporated into other learning approaches. We show that the proposed hybrid model outperforms state of the art on several standard benchmarks, including CIFAR-10, CIFAR-100, and Mini-Imagenet. Furthermore, the performance gain consistently increases with the reduction in the amount of labeled data, as well as in the presence of bias. We also show that MUSCLE has the potential to boost the classification performance when used in the fine-tuning phase for a model pre-trained only on unlabeled data.