English

Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis

Machine Learning 2025-07-22 v2 Artificial Intelligence

Abstract

Deep neural networks (DNNs) deliver outstanding performance, but their complexity often prohibits deployment in resource-constrained settings. Comprehensive structured pruning frameworks based on parameter dependency analysis reduce model size with specific regard to computational performance. When applying them to Multi-Component Neural Architectures (MCNAs), they risk network integrity by removing large parameter groups. We introduce a component-aware pruning strategy, extending dependency graphs to isolate individual components and inter-component flows. This creates smaller, targeted pruning groups that conserve functional integrity. Demonstrated effectively on a control task, our approach achieves greater sparsity and reduced performance degradation, opening a path for optimizing complex, multi-component DNNs efficiently.

Keywords

Cite

@article{arxiv.2504.13296,
  title  = {Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis},
  author = {Ganesh Sundaram and Jonas Ulmen and Daniel Görges},
  journal= {arXiv preprint arXiv:2504.13296},
  year   = {2025}
}

Comments

6 pages, IFAC J3C, 2025

R2 v1 2026-06-28T23:02:37.932Z