Hardware-Aware Evolutionary Explainable Filter Pruning for Convolutional Neural Networks
Open Access
- 22 February 2024
- journal article
- research article
- Published by Springer Nature in International Journal of Parallel Programming
- Vol. 52 (1-2) , 40-58
Abstract
Filter pruning of convolutional neural networks (CNNs) is a common technique to effectively reduce the memory footprint, the number of arithmetic operations, and, consequently, inference time. Recent pruning approaches also consider the targeted device (i.e., graphics processing units) for CNN deployment to reduce the actual inference time. However, simple metrics, such as the $$\ell ^1$$ -norm, are used for deciding which filters to prune. In this work, we propose a hardware-aware technique to explore the vast multi-objective design space of possible filter pruning configurations. Our approach incorporates not only the targeted device but also techniques from explainable artificial intelligence for ranking and deciding which filters to prune. For each layer, the number of filters to be pruned is optimized with the objective of minimizing the inference time and the error rate of the CNN. Experimental results show that our approach can speed up inference time by 1.40× and 1.30× for VGG-16 on the CIFAR-10 dataset and ResNet-18 on the ILSVRC-2012 dataset, respectively, compared to the state-of-the-art ABCPruner.
Keywords
Funding Information
- Bundesministerium für Forschung, Technologie und Raumfahrt (01IS19070)
- Friedrich-Alexander-Universität Erlangen-Nürnberg
This publication has 18 references indexed in Scilit:
- MOSP: Multi-Objective Sensitivity Pruning of Deep Neural Networks2022
- Hardware-Aware Evolutionary Filter Pruning2022
- Blackthorn: Latency Estimation Framework for CNNs on Embedded Nvidia PlatformsIEEE Access, 2021
- A Safari through FPGA-based Neural Network Compilation and Design Automation Flows2021
- Design Space Exploration of Time, Energy, and Error Rate Trade-offs for CNNs Using Accuracy-Programmable Instruction Set Processors2021
- Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs2019
- Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture Search2019
- Deep Residual Learning for Image Recognition2016
- A fast and elitist multiobjective genetic algorithm: NSGA-IIIEEE Transactions on Evolutionary Computation, 2002
- Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approachIEEE Transactions on Evolutionary Computation, 1999