ECQ$^{\text {x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
Open Access
- 17 April 2022
- book chapter
- Published by Springer Nature
- p. 271-296
Abstract
The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increases in memory and computational demands make deep learning prohibitive for resource-constrained hardware platforms such as mobile devices. Recent efforts aim to reduce these overheads, while preserving model performance as much as possible, and include parameter reduction techniques, parameter quantization, and lossless compression techniques.In this chapter, we develop and describe a novel quantization paradigm for DNNs: Our method leverages concepts of explainable AI (XAI) and concepts of information theory: Instead of assigning weight values based on their distances to the quantization clusters, the assignment function additionally considers weight relevances obtained from Layer-wise Relevance Propagation (LRP) and the information content of the clusters (entropy optimization). The ultimate goal is to preserve the most relevant weights in quantization clusters of highest information content.Experimental results show that this novel Entropy-Constrained and XAI-adjusted Quantization (ECQ $$^{\text {x}}$$ ) method generates ultra low-precision (2–5 bit) and simultaneously sparse neural networks while maintaining or even improving model performance. Due to reduced parameter precision and high number of zero-elements, the rendered networks are highly compressible in terms of file size, up to 103 $$\times $$ compared to the full-precision unquantized DNN model. Our approach was evaluated on different types of models and datasets (including Google Speech Commands, CIFAR-10 and Pascal VOC) and compared with previous work.
Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- MobileNetV2: Inverted Residuals and Linear Bottlenecks2018
- Methods for interpreting and understanding deep neural networksDigital Signal Processing, 2018
- Efficient Processing of Deep Neural Networks: A Tutorial and SurveyProceedings of the IEEE, 2017
- Channel Pruning for Accelerating Very Deep Neural Networks2017
- Weighted-Entropy-Based Quantization for Deep Neural Networks2017
- In situ click chemistry generation of cyclooxygenase-2 inhibitorsNature Communications, 2017
- Deep Residual Learning for Image Recognition2016
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- 1.1 Computing's energy problem (and what we can do about it)2014
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948