Steerable Zero-Shot Neural Architecture Search for Efficient Edge Inference
Loading...
Author
Narduzzi, Simon
Vuagniaux, Rémy
Sharma, Kishan
Liu, Shih-Chii
Dunbar, L. Andrea
DOI
10.1109/ISCAS56072.2025.11044278
Abstract
Recent advancements in Neural Architecture Search (NAS) have introduced methods capable of identifying optimal neural network architectures in minutes on Graphical Processing Units (GPUs) using zero-shot proxies, but mainly focus on single-objective optimization. NAS is also used to discover efficient architectures for edge devices. However, addressing the diverse hardware and application constraints specific to edge platforms remains a significant challenge. In this paper, we introduce a zero-shot NAS approach designed to generate hardware-aware architectures, combined with a selection technique that allows adaptable model optimization across various deployment scenarios without re-executing the search. We demonstrate the flexibility of our solution by benchmarking the Google Coral Edge Tensor Processing Unit (TPU). Our technique led to the efficient exploration of the architecture space of NAS-Bench-201 (NB201) in under a minute, accelerating the search by 25× compared to previous work while maintaining comparable accuracies of 93.24% on CIFAR-10 and 42.99% on ImageNet16-120.
Publication Reference
2025 IEEE International Symposium on Circuits and Systems (ISCAS), London, UK, pp. 1-5.
Year
2025-05-26
Sponsors
This work has received funding from the Swiss State Secretariat for Education, Research, and Innovation (SERI). This work was partially funded by EU H2020, through ANDANTE grant no. 876925. This work has been partially funded by the EU Project dAIEDGE (GA Nr 101120726).