Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity
This work addresses the problem of reducing search costs for designing efficient deep learning architectures tailored to specific hardware, particularly for edge devices, but it is incremental as it builds on existing representation similarity methods.
The paper tackles the high computational cost of hardware-aware neural architecture search (HW-NAS) by proposing MO-HDNAS, a multi-objective method that optimizes representation similarity, hardware cost, and hardware cost diversity to identify trade-off architectures in a single run, achieving efficient results across six edge devices for image classification.
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.