Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers

Jianbo Ye, Xin Lu, Zhe Lin, James Z. Wang

Feb 15, 2018 (modified: Feb 22, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a smaller-norm parameter or feature plays a less informative role at the inference time. In this paper, we propose a channel pruning technique for accelerating the computations of deep convolutional neural networks (CNNs) that does not critically rely on this assumption. Instead, it focuses on direct simplification of the channel-to-channel computation graph of a CNN without the need of performing a computationally difficult and not-always-useful task of making high-dimensional tensors of CNN structured sparse. Our approach takes two stages: first to adopt an end-to-end stochastic training method that eventually forces the outputs of some channels to be constant, and then to prune those constant channels from the original neural network by adjusting the biases of their impacting layers such that the resulting compact model can be quickly fine-tuned. Our approach is mathematically appealing from an optimization perspective and easy to reproduce. We experimented our approach through several image learning benchmarks and demonstrate its interest- ing aspects and competitive performance.
  • TL;DR: A CNN model pruning method using ISTA and rescaling trick to enforce sparsity of scaling parameters in batch normalization.
  • Keywords: model pruning, batch normalization, convolutional neural network, ISTA