Summary of Paoding: a High-fidelity Data-free Pruning Toolkit For Debloating Pre-trained Neural Networks, by Mark Huasong Meng et al.
PAODING: A High-fidelity Data-free Pruning Toolkit for Debloating Pre-trained Neural Networks
by Mark Huasong Meng, Hao Guan, Liuhuo Wan, Sin Gee Teo, Guangdong Bai, Jin Song Dong
First submitted to arxiv on: 30 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Software Engineering (cs.SE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary PAODING, a toolkit for debloating pretrained neural network models through data-free pruning, is presented in this paper. The iterative process used by PAODING dynamically measures the impact of deleting neurons to identify those with minimal effect on the output layer, allowing for significant reduction in model size while preserving test accuracy and adversarial robustness. Evaluation shows generalizability across different datasets and models. PAODING is publicly available on PyPI. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary PAODING is a new tool that helps make neural networks smaller without losing their ability to work well. It does this by carefully removing parts of the network that don’t affect how it works much. The results show that PAODING can make models smaller while still keeping them accurate and robust against bad inputs. This toolkit is useful for many applications, including those that need to run on devices with limited resources. |
Keywords
» Artificial intelligence » Neural network » Pruning
