# Galaxy Morphology Classification with Counterfactual Explanation

arXiv: https://arxiv.org/abs/2510.14655 · HTML: https://mlsanity.com/paper/2510.14655/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 16 Oct 2025.

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

- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [InfoVAE: Information Maximizing Variational Autoencoders](https://mlsanity.com/paper/1706.02262/) (2017)
- [ECINN: Efficient Counterfactuals from Invertible Neural Networks](https://mlsanity.com/paper/2103.13701/) (2021)
- [E(2) Equivariant Neural Networks for Robust Galaxy Morphology Classification](https://mlsanity.com/paper/2311.01500/) (2023)
- [Detection of extragalactic Ultra-Compact Dwarfs and Globular Clusters using Explainable AI techniques](https://mlsanity.com/paper/2201.01604/) (2022)

## Built on by (most cited first, 1 of 1)

- [Residual-Space Evolutionary Optimization via Flow-based Generative Models](https://mlsanity.com/paper/2606.20084/) (2026)

## Abstract (arXiv)

Galaxy morphologies play an essential role in the study of the evolution of galaxies. The determination of morphologies is laborious for a large amount of data giving rise to machine learning-based approaches. Unfortunately, most of these approaches offer no insight into how the model works and make the results difficult to understand and explain. We here propose to extend a classical encoder-decoder architecture with invertible flow, allowing us to not only obtain a good predictive performance but also provide additional information about the decision process with counterfactual explanations.