# Structural Analysis of Sparse Neural Networks

arXiv: https://arxiv.org/abs/1910.07225 · HTML: https://mlsanity.com/paper/1910.07225/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2019.

## Built on by (most cited first, 8 of 8)

- [Beyond Multilayer Perceptrons: Investigating Complex Topologies in Neural Networks](https://mlsanity.com/paper/2303.17925/) (2023)
- [Experiments on Properties of Hidden Structures of Sparse Neural Networks](https://mlsanity.com/paper/2107.12917/) (2021)
- [Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations](https://mlsanity.com/paper/2305.16886/) (2023)
- [Correlation Analysis between the Robustness of Sparse Neural Networks and their Random Hidden Structural Priors](https://mlsanity.com/paper/2107.06158/) (2021)
- [deepstruct -- linking deep learning and graph theory](https://mlsanity.com/paper/2111.06679/) (2021)
- [Evolving Neural Networks with Optimal Balance between Information Flow and Connections Cost](https://mlsanity.com/paper/2202.06163/) (2022)
- [Neuron-centric Hebbian Learning](https://mlsanity.com/paper/2403.12076/) (2024)
- [Efficient NAS with FaDE on Hierarchical Spaces](https://mlsanity.com/paper/2404.16218/) (2024)

## Abstract (arXiv)

Sparse Neural Networks regained attention due to their potential for mathematical and computational advantages. We give motivation to study Artificial Neural Networks (ANNs) from a network science perspective, provide a technique to embed arbitrary Directed Acyclic Graphs into ANNs and report study results on predicting the performance of image classifiers based on the structural properties of the networks' underlying graph. Results could further progress neuroevolution and add explanations for the success of distinct architectures from a structural perspective.