Beyond One-Way Pruning: Bidirectional Pruning-Regrowth for Extreme Accuracy-Sparsity Tradeoff
Year: 2025
Type: preprint
Abstract: As a widely adopted model compression technique, model pruning has demonstrated strong effectiveness across various architectures. However, we observe that when sparsity exceeds a certain threshold, both iterative and one-shot pruning methods lead to a steep decline in model performance. This rapid degradation limits the achievable compression ratio and prevents models from meeting the stringent size constraints required by certain hardware platforms, rendering them inoperable. To overcome this limitation, we propose a bidirectional pruning-regrowth strategy. Starting from an extremely compressed network that satisfies hardware constraints, the method selectively regenerates critical connections to recover lost performance, effectively mitigating the sharp accuracy drop commonly observed under high sparsity conditions.
Source: arXiv (Cornell University)
Authors: Liu, Junchen, Sheng, Yi
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416349190
Cites:
Cited by:
Related to: