DMCP: Differentiable Markov Channel Pruning for Neural Networks
This work addresses the computational inefficiency in channel pruning for deep learning practitioners, offering a novel differentiable approach that is incremental in improving existing pruning techniques.
The paper tackles the problem of efficiently searching for optimal sub-structures in channel pruning for neural networks, proposing DMCP, a differentiable method that models pruning as a Markov process and achieves consistent improvements over state-of-the-art methods on ImageNet with ResNet and MobileNetV2 across various FLOPs settings.
Recent works imply that the channel pruning can be regarded as searching optimal sub-structure from unpruned networks. However, existing works based on this observation require training and evaluating a large number of structures, which limits their application. In this paper, we propose a novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP), to efficiently search the optimal sub-structure. Our method is differentiable and can be directly optimized by gradient descent with respect to standard task loss and budget regularization (e.g. FLOPs constraint). In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process. In the end, our method is able to implicitly select the proper number of channels in each layer by the Markov process with optimized transitions. To validate the effectiveness of our method, we perform extensive experiments on Imagenet with ResNet and MobilenetV2. Results show our method can achieve consistent improvement than state-of-the-art pruning methods in various FLOPs settings. The code is available at https://github.com/zx55/dmcp