# Insights on Galaxy Evolution from Interpretable Sparse Feature Networks

arXiv: https://arxiv.org/abs/2501.00089 · HTML: https://mlsanity.com/paper/2501.00089/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 55 references that are in the map.
- First posted on arXiv 30 Dec 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [k-Sparse Autoencoders](https://mlsanity.com/paper/1312.5663/) (2013)
- [fastai: A Layered API for Deep Learning](https://mlsanity.com/paper/2002.04688/) (2020)
- [The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision](https://mlsanity.com/paper/2406.03662/) (2024)
- [Ranger21: a synergistic deep learning optimizer](https://mlsanity.com/paper/2106.13731/) (2021)
- [Attention-gating for improved radio galaxy classification](https://mlsanity.com/paper/2012.01248/) (2020)
- [Galaxy spectroscopy without spectra: Galaxy properties from photometric images with conditional diffusion models](https://mlsanity.com/paper/2406.18175/) (2024)
- [CMasher: Scientific colormaps for making accessible, informative and 'cmashing' plots](https://mlsanity.com/paper/2003.01069/) (2020)

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

- [Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders](https://mlsanity.com/paper/2510.23749/) (2025)
- [A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshifts](https://mlsanity.com/paper/2608.23626/) (2026)

## Abstract (arXiv)

Galaxy appearances reveal the physics of how they formed and evolved. Machine learning models can now exploit galaxies' information-rich morphologies to predict physical properties directly from image cutouts. Learning the relationship between pixel-level features and galaxy properties is essential for building a physical understanding of galaxy evolution, but we are still unable to explicate the details of how deep neural networks represent image features. To address this lack of interpretability, we present a novel neural network architecture called a Sparse Feature Network (SFNet). SFNets produce interpretable features that can be linearly combined in order to estimate galaxy properties like optical emission line ratios or gas-phase metallicity. We find that SFNets do not sacrifice accuracy in order to gain interpretability, and that they perform comparably well to cutting-edge models on astronomical machine learning tasks. Our novel approach is valuable for finding physical patterns in large datasets and helping astronomers interpret machine learning results.