-
[pdf]
[arXiv]
[bibtex]@InProceedings{Sinha_2024_CVPR, author = {Sinha, Nilotpal and Rostami, Peyman and El Rahman Shabayek, Abd and Kacem, Anis and Aouada, Djamila}, title = {Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {8032-8039} }
Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity
Abstract
Hardware-aware Neural Architecture Search approaches (HW-NAS) automate the design of deep learning architectures tailored specifically to a given target hardware platform. Yet these techniques demand substantial computational resources primarily due to the expensive process of assessing the performance of identified architectures. To alleviate this problem a recent direction in the literature has employed representation similarity metric for efficiently evaluating architecture performance. Nonetheless since it is inherently a single objective method it requires multiple runs to identify the optimal architecture set satisfying the diverse hardware cost constraints thereby increasing the search cost. Furthermore simply converting the single objective into a multi-objective approach results in an under-explored architectural search space. In this study we propose a Multi-Objective method to address the HW-NAS problem called MO-HDNAS to identify the trade-off set of architectures in a single run with low computational cost. This is achieved by optimizing three objectives: maximizing the representation similarity metric minimizing hardware cost and maximizing the hardware cost diversity. The third objective i.e. hardware cost diversity is used to facilitate a better exploration of the architecture search space. Experimental results demonstrate the effectiveness of our proposed method in efficiently addressing the HW-NAS problem across six edge devices for the image classification task.
Related Material