# Data Aware Neural Architecture Search

arXiv: https://arxiv.org/abs/2304.01821 · HTML: https://mlsanity.com/paper/2304.01821/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2023.

## Built on by (most cited first, 4 of 4)

- [A Machine Learning-oriented Survey on Tiny Machine Learning](https://mlsanity.com/paper/2309.11932/) (2023)
- [Fast Data Aware Neural Architecture Search via Supernet Accelerated Evaluation](https://mlsanity.com/paper/2502.12690/) (2025)
- [Wake Vision: A Tailored Dataset and Benchmark Suite for TinyML Computer Vision Applications](https://mlsanity.com/paper/2405.00892/) (2024)
- [Data Aware Differentiable Neural Architecture Search for Tiny Keyword Spotting Applications](https://mlsanity.com/paper/2507.15545/) (2025)

## Abstract (arXiv)

Neural Architecture Search (NAS) is a popular tool for automatically generating Neural Network (NN) architectures. In early NAS works, these tools typically optimized NN architectures for a single metric, such as accuracy. However, in the case of resource constrained Machine Learning, one single metric is not enough to evaluate a NN architecture. For example, a NN model achieving a high accuracy is not useful if it does not fit inside the flash memory of a given system. Therefore, recent works on NAS for resource constrained systems have investigated various approaches to optimize for multiple metrics. In this paper, we propose that, on top of these approaches, it could be beneficial for NAS optimization of resource constrained systems to also consider input data granularity. We name such a system "Data Aware NAS", and we provide experimental evidence of its benefits by comparing it to traditional NAS.