Tensorizing Neural Networks

TL;DR

This paper introduces a method to compress neural network layers using Tensor Train format, significantly reducing memory requirements while maintaining performance, enabling deployment on low-resource devices.

Contribution

It proposes tensorizing fully-connected layers with Tensor Train format, achieving massive parameter reduction without sacrificing network expressiveness.

Findings

Up to 200,000x compression of weight matrices

Whole network compression up to 7x

Preserved accuracy with reduced parameters

Abstract

Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required by commonly used fully-connected layers, making it hard to use the models on low-end devices and stopping the further increase of the model size. In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of the layer is preserved. In particular, for the Very Deep VGG networks we report the compression factor of the dense weight matrix of a fully-connected layer up to 200000 times leading to the compression factor of the whole network up to 7 times.