Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis
Year: 2025
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Sundaram, Ganesh, Ulmen, Jonas, Görges, Daniel
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6929406103
Cites:
Cited by:
Related to: