The paper presents PAODING, a toolkit for data-free pruning of pre-trained neural network models. The key highlights are:
PAODING adopts an iterative pruning process that dynamically measures the effect of deleting a neuron to identify candidates that have the least impact on the output layer. This is done to preserve the model fidelity.
For convolutional (Conv2D) layers, PAODING uses a scale-based sampling strategy that prioritizes pruning the least salient channels. For dense layers, it uses a pair-wise pruning mechanism based on the impact of pruning a neuron pair on the model outputs.
Evaluation on four neural network models (a small MLP and three CNNs) shows that PAODING can significantly reduce the model size (up to 4.5x) while preserving test accuracy (less than 50% decay) and adversarial robustness (maintaining over 50% of original robustness).
PAODING is implemented in Python and is publicly available on PyPI. It is compatible with various neural network models trained using TensorFlow and can be further optimized using techniques like quantization.
In eine andere Sprache
aus dem Quellinhalt
arxiv.org
Wichtige Erkenntnisse aus
by Mark Huasong... um arxiv.org 05-02-2024
https://arxiv.org/pdf/2405.00074.pdfTiefere Fragen