Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks
arXiv:1904.10921
Abstract
Architecture optimization, which is a technique for finding an efficient neural network that meets certain requirements, generally reduces to a set of multiple-choice selection problems among alternative sub-structures or parameters. The discrete nature of the selection problem, however, makes this optimization difficult. To tackle this problem we introduce a novel concept of a trainable gate function. The trainable gate function, which confers a differentiable property to discretevalued variables, allows us to directly optimize loss functions that include non-differentiable discrete values such as 0-1 selection. The proposed trainable gate can be applied to pruning. Pruning can be carried out simply by appending the proposed trainable gate functions to each intermediate output tensor followed by fine-tuning the overall model, using any gradient-based training methods. So the proposed method can jointly optimize the selection of the pruned channels while fine-tuning the weights of the pruned model at the same time. Our experimental results demonstrate that the proposed method efficiently optimizes arbitrary neural networks in various tasks such as image classification, style transfer, optical flow estimation, and neural machine translation.
Accepted to AAAI 2020 (Poster)
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Neural Architecture Search with Reinforcement Learning
- Categorical Reparameterization with Gumbel-Softmax
- DARTS: Differentiable Architecture Search
- Pruning Convolutional Neural Networks for Resource Efficient Inference
- A Learned Representation For Artistic Style
- Channel Pruning for Accelerating Very Deep Neural Networks
- Bayesian Compression for Deep Learning
- Neural Combinatorial Optimization with Reinforcement Learning
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling
- Compressing Neural Networks using the Variational Information Bottleneck
- Progressive Weight Pruning of Deep Neural Networks using ADMM