Compressing RNNs for IoT devices by 15-38x using Kronecker Products

TL;DR

This paper presents a novel Kronecker product-based method to significantly compress RNNs for IoT devices, achieving 15-50x reduction with minimal accuracy loss and improved inference speed.

Contribution

Introduces Kronecker product-based RNN compression technique that outperforms existing methods in size reduction and accuracy preservation, with a hybrid approach for fine-grained control.

Findings

Achieves 15-38x compression with minimal accuracy loss.

Further compresses models to 50x with 8-bit quantization.

Outperforms state-of-the-art methods across multiple benchmarks.

Abstract

Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size.As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy. This paper introduces a method to compress RNNs for resource constrained environments using Kronecker product (KP). KPs can compress RNN layers by 15-38x with minimal accuracy loss. By quantizing the resulting models to 8-bits, we further push the compression factor to 50x. We show that KP can beat the task accuracy achieved by other state-of-the-art compression techniques across 5 benchmarks spanning 3 different applications, while simultaneously improving inference run-time. We show that the KP compression mechanism does introduce an accuracy loss, which can be mitigated by a proposed hybrid KP (HKP) approach. Our HKP algorithm provides fine-grained control over the compression ratio, enabling us to regain accuracy lost during compression by adding a small number of model parameters.