PAODING: A High-fidelity Data-free Pruning Toolkit for Debloating Pre-trained Neural Networks

arXiv:2405.00074v1 Announce Type: new
Abstract: We present PAODING, a toolkit to debloat pretrained neural network models through the lens of data-free pruning. To preserve the model fidelity, PAODING adopts an iterative process, which dynamically measures the effect of deleting a neuron to identify candidates that have the least impact to the output layer. Our evaluation shows that PAODING can significantly reduce the model size, generalize on different datasets and models, and meanwhile preserve the model fidelity in terms of test …

arxiv cs.lg cs.se data fidelity free networks neural networks pruning toolkit type