Recurrent Parameter Generators

Jiayun Wang, Yubei Chen, Stella Yu, Brian Cheung, Yann LeCun

Keywords: recurrent, parameters, degrees of freedom

Abstract: We present a generic method for recurrently using the same parameters for many different convolution layers to build a deep network. Specifically, for a network, we create a recurrent parameter generator (RPG), from which the parameters of each convolution layer are generated. Though using recurrent models to build a deep convolutional neural network (CNN) is not entirely new, our method achieves significant performance gain compared to the existing works. We demonstrate how to build a one-layer-size neural network to achieve similar performance compared to other traditional CNN models on various applications and datasets. We use the RPG to build a ResNet18 network with the number of weights equivalent to one convolutional layer of a conventional ResNet and show this model can achieve $67.2\%$ ImageNet top-1 accuracy. Additionally, such a method allows us to build an arbitrarily complex neural network with any amount of parameters. For example, we build a ResNet34 with model parameters reduced by more than $400$ times, which still achieves $41.6\%$ ImageNet top-1 accuracy. Furthermore, the RPG can be further pruned and quantized for better run-time performance in addition to the model size reduction. We provide a new perspective for model compression. Rather than shrinking parameters from a large model, RPG sets a certain parameter-size constraint and uses the gradient descent algorithm to automatically find the best model under the constraint. Extensive experiment results are provided to demonstrate the power of the proposed recurrent parameter generator.

One-sentence Summary: A generic method for generate a network with any degrees of freedom via a recurrent parameter generator