# Landscape of Neural Architecture Search across sensors: how much do they differ ?

arXiv: https://arxiv.org/abs/2201.06321 · HTML: https://mlsanity.com/paper/2201.06321/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 23 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 12 of 12)

- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://mlsanity.com/paper/1902.09635/) (2019)
- [Deep learning in remote sensing: a review](https://mlsanity.com/paper/1710.03959/) (2017)
- [More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification](https://mlsanity.com/paper/2008.05457/) (2020)
- [NAS evaluation is frustratingly hard](https://mlsanity.com/paper/1912.12522/) (2019)
- [Best Practices for Scientific Research on Neural Architecture Search](https://mlsanity.com/paper/1909.02453/) (2019)
- [Learning Spectral-Spatial-Temporal Features via a Recurrent Convolutional Neural Network for Change Detection in Multispectral Imagery](https://mlsanity.com/paper/1803.02642/) (2018)
- [Metaheuristic Design of Feedforward Neural Networks: A Review of Two Decades of Research](https://mlsanity.com/paper/1705.05584/) (2017)
- [R3-Net: A Deep Network for Multi-oriented Vehicle Detection in Aerial Images and Videos](https://mlsanity.com/paper/1808.05560/) (2018)
- [Bayesian Neural Architecture Search using A Training-Free Performance Metric](https://mlsanity.com/paper/2001.10726/) (2020)
- [Fitness Landscape Footprint: A Framework to Compare Neural Architecture Search Problems](https://mlsanity.com/paper/2111.01584/) (2021)
- [A Data-driven Approach to Neural Architecture Search Initialization](https://mlsanity.com/paper/2111.03524/) (2021)

## Built on by (most cited first, 1 of 1)

- [HPO: We won't get fooled again](https://mlsanity.com/paper/2208.03320/) (2022)

## Abstract (arXiv)

With the rapid rise of neural architecture search, the ability to understand its complexity from the perspective of a search algorithm is desirable. Recently, Traor'e et al. have proposed the framework of Fitness Landscape Footprint to help describe and compare neural architecture search problems. It attempts at describing why a search strategy might be successful, struggle or fail on a target task. Our study leverages this methodology in the context of searching across sensors, including sensor data fusion. In particular, we apply the Fitness Landscape Footprint to the real-world image classification problem of So2Sat LCZ42, in order to identify the most beneficial sensor to our neural network hyper-parameter optimization problem. From the perspective of distributions of fitness, our findings indicate a similar behaviour of the search space for all sensors: the longer the training time, the larger the overall fitness, and more flatness in the landscapes (less ruggedness and deviation). Regarding sensors, the better the fitness they enable (Sentinel-2), the better the search trajectories (smoother, higher persistence). Results also indicate very similar search behaviour for sensors that can be decently fitted by the search space (Sentinel-2 and fusion).