EMNAPE: efficient multi-dimensional neural architecture pruning for EdgeAI

• Main Authors: Kong, Hao, Luo, Xiangzhong, Huai, Shuo, Liu, Di, Subramaniam, Ravi, Makaya, Christian, Lin, Qian, Liu, Weichen
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Heuristic Algorithms; Computational Modeling
• Online Access: https://hdl.handle.net/10356/167488
• Institution: Nanyang Technological University

In this paper, we propose a multi-dimensional pruning framework, EMNAPE, to jointly prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In EMNAPE, we introduce a two-stage evaluation strategy to evaluate the importance of each pruning unit and identify the computational redundancy in the three dimensions. Based on the evaluation strategy, we further present a heuristic pruning algorithm to progressively prune redundant units from the three dimensions for better accuracy and efficiency. Experiments demonstrate the superiority of EMNAPE over existing methods.