Structural Analysis of Sparse Neural Networks

Julian Stier, Michael Granitzer

2019-10-16Neural Architecture Search

Abstract

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.

Results

Task	Dataset	Metric	Value	Model
Neural Architecture Search	MNIST	R2	0.9314	Sparse Neural Network
AutoML	MNIST	R2	0.9314	Sparse Neural Network

Related Papers

DASViT: Differentiable Architecture Search for Vision Transformer2025-07-17 AnalogNAS-Bench: A NAS Benchmark for Analog In-Memory Computing2025-06-23 From Tiny Machine Learning to Tiny Deep Learning: A Survey2025-06-21 One-Shot Neural Architecture Search with Network Similarity Directed Initialization for Pathological Image Classification2025-06-17 DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification2025-06-17 MARCO: Hardware-Aware Neural Architecture Search for Edge Devices with Multi-Agent Reinforcement Learning and Conformal Prediction Filtering2025-06-16 Finding Optimal Kernel Size and Dimension in Convolutional Neural Networks An Architecture Optimization Approach2025-06-16 Directed Acyclic Graph Convolutional Networks2025-06-13