Layer-Specific Optimization: Sensitivity Based Convolution Layers Basis Search
This work addresses the challenge of deploying large neural networks on resource-constrained devices, though it appears incremental as it builds on existing matrix decomposition techniques.
The paper tackles the problem of reducing the size and computational cost of overparameterized deep neural networks by proposing a method to apply matrix decomposition to convolutional layers, training only a subset as basis convolutions and representing others as linear combinations. Experiments on ResNet models with CIFAR-10 show that this approach reduces model size and accelerates forward and backward passes.
Deep neural network models have a complex architecture and are overparameterized. The number of parameters is more than the whole dataset, which is highly resource-consuming. This complicates their application and limits its usage on different devices. Reduction in the number of network parameters helps to reduce the size of the model, but at the same time, thoughtlessly applied, can lead to a deterioration in the quality of the network. One way to reduce the number of model parameters is matrix decomposition, where a matrix is represented as a product of smaller matrices. In this paper, we propose a new way of applying the matrix decomposition with respect to the weights of convolutional layers. The essence of the method is to train not all convolutions, but only the subset of convolutions (basis convolutions), and represent the rest as linear combinations of the basis ones. Experiments on models from the ResNet family and the CIFAR-10 dataset demonstrate that basis convolutions can not only reduce the size of the model but also accelerate the forward and backward passes of the network. Another contribution of this work is that we propose a fast method for selecting a subset of network layers in which the use of matrix decomposition does not degrade the quality of the final model.