Book ; Online: Importance Estimation with Random Gradient for Neural Network Pruning
2023
Abstract: Global Neuron Importance Estimation is used to prune neural networks for efficiency reasons. To determine the global importance of each neuron or convolutional kernel, most of the existing methods either use activation or gradient information or both, ... ...
Abstract | Global Neuron Importance Estimation is used to prune neural networks for efficiency reasons. To determine the global importance of each neuron or convolutional kernel, most of the existing methods either use activation or gradient information or both, which demands abundant labelled examples. In this work, we use heuristics to derive importance estimation similar to Taylor First Order (TaylorFO) approximation based methods. We name our methods TaylorFO-abs and TaylorFO-sq. We propose two additional methods to improve these importance estimation methods. Firstly, we propagate random gradients from the last layer of a network, thus avoiding the need for labelled examples. Secondly, we normalize the gradient magnitude of the last layer output before propagating, which allows all examples to contribute similarly to the importance score. Our methods with additional techniques perform better than previous methods when tested on ResNet and VGG architectures on CIFAR-100 and STL-10 datasets. Furthermore, our method also complements the existing methods and improves their performances when combined with them. Comment: 7 pages, 2 figures, ICLR 2023 Workshop on Sparsity in Neural Networks. arXiv admin note: text overlap with arXiv:2306.13203 |
---|---|
Keywords | Computer Science - Machine Learning |
Subject code | 510 |
Publishing date | 2023-10-31 |
Publishing country | us |
Document type | Book ; Online |
Database | BASE - Bielefeld Academic Search Engine (life sciences selection) |
Full text online
More links
Kategorien
Inter-library loan at ZB MED
Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.