# Twin Neural Network Regression

arXiv: https://arxiv.org/abs/2012.14873 · HTML: https://mlsanity.com/paper/2012.14873/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Twin Neural Network Regression is a Semi-Supervised Regression Algorithm](https://mlsanity.com/paper/2106.06124/) (2021)
- [Applying the Case Difference Heuristic to Learn Adaptations from Deep Network Features](https://mlsanity.com/paper/2107.07095/) (2021)
- [Twin Neural Network Improved k-Nearest Neighbor Regression](https://mlsanity.com/paper/2310.00664/) (2023)
- [Pairwise Difference Learning for Classification](https://mlsanity.com/paper/2406.20031/) (2024)
- [Inverting Non-Injective Functions with Twin Neural Network Regression](https://mlsanity.com/paper/2601.05378/) (2026)
- [Differential Learning for Robust Prediction of Thermal Stability with Application to Energetic Materials](https://mlsanity.com/paper/2608.23874/) (2026)

## Abstract (arXiv)

We introduce twin neural network (TNN) regression. This method predicts differences between the target values of two different data points rather than the targets themselves. The solution of a traditional regression problem is then obtained by averaging over an ensemble of all predicted differences between the targets of an unseen data point and all training data points. Whereas ensembles are normally costly to produce, TNN regression intrinsically creates an ensemble of predictions of twice the size of the training set while only training a single neural network. Since ensembles have been shown to be more accurate than single models this property naturally transfers to TNN regression. We show that TNNs are able to compete or yield more accurate predictions for different data sets, compared to other state-of-the-art methods. Furthermore, TNN regression is constrained by self-consistency conditions. We find that the violation of these conditions provides an estimate for the prediction uncertainty.