# Partition of Unity Neural Networks for Interpretable Classification with Explicit Class Regions

arXiv: https://arxiv.org/abs/2602.00511 · HTML: https://mlsanity.com/paper/2602.00511/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [Provable approximation properties for deep neural networks](https://mlsanity.com/paper/1509.07385/) (2015)
- [Stick-Breaking Variational Autoencoders](https://mlsanity.com/paper/1605.06197/) (2016)
- [Partition of unity networks: deep hp-approximation](https://mlsanity.com/paper/2101.11256/) (2021)

## Abstract (arXiv)

We introduce Partition of Unity Neural Networks (PUNNs), a neural-network architecture for multiclass classification based on the classical mathematical notion of a partition of unity. The starting point is the observation that the characteristic functions of ideal class regions form a partition of unity. PUNNs replace these discontinuous indicators by learned continuous functions [ h1,ldots,hC:mathcal X→[0,1] ] whose sum is identically one and whose values are interpreted directly as class probabilities. The partition functions are generated through a recursive family of input-dependent gates. This construction guarantees nonnegative class probabilities summing to one without a separate normalization layer such as softmax, while providing an explicit ordered factorization of each probability in terms of the gate values. The resulting gate trace gives an interpretable representation of how individual class probabilities are formed. The framework also allows multiple partition functions to represent a single class and admits both neural-network and geometry-informed realizations of the gates. We prove that PUNNs are dense in the space of continuous probability maps from compact subsets of mathbb Rd into the probability simplex. Thus, the recursive partition-of-unity structure retains universal approximation of continuous probabilistic classifiers, including maps whose components may vanish. Numerical experiments on synthetic datasets, MNIST, and CIFAR-100 illustrate the learned partitions, the effect of class ordering, and the use of multiple partition components per class. We also develop shape-informed gates that incorporate geometric information directly; when the chosen geometry is well matched to the class regions, these models achieve comparable accuracy with substantially fewer trainable parameters.