MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
This addresses the problem of reducing computational cost and human effort in neural network pruning for researchers and practitioners, though it is incremental as it builds on existing pruning and meta learning techniques.
The paper tackles automatic channel pruning of deep neural networks by proposing a meta learning approach that trains a PruningNet to generate weights for pruned structures, enabling efficient evolutionary search without finetuning. It demonstrates superior performance on MobileNet V1/V2 and ResNet compared to state-of-the-art methods.
In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generate weight parameters for any pruned structure given the target network. We use a simple stochastic structure sampling method for training the PruningNet. Then, we apply an evolutionary procedure to search for good-performing pruned networks. The search is highly efficient because the weights are directly generated by the trained PruningNet and we do not need any finetuning at search time. With a single PruningNet trained for the target network, we can search for various Pruned Networks under different constraints with little human participation. Compared to the state-of-the-art pruning methods, we have demonstrated superior performances on MobileNet V1/V2 and ResNet. Codes are available on https://github.com/liuzechun/MetaPruning.