# A Novel Evolutionary Algorithm for Hierarchical Neural Architecture Search

arXiv: https://arxiv.org/abs/2107.08484 · HTML: https://mlsanity.com/paper/2107.08484/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 11 references that are in the map.
- First posted on arXiv 18 Jul 2021.

## Builds on (most cited first, 7 of 7)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://mlsanity.com/paper/1902.09635/) (2019)
- [Hierarchical Representations for Efficient Architecture Search](https://mlsanity.com/paper/1711.00436/) (2017)
- [A Survey on Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2008.10937/) (2020)
- [Evolutionary Architecture Search For Deep Multitask Networks](https://mlsanity.com/paper/1803.03745/) (2018)
- [Fine-Tuning DARTS for Image Classification](https://mlsanity.com/paper/2006.09042/) (2020)
- [Improving Neuroevolution Using Island Extinction and Repopulation](https://mlsanity.com/paper/2005.07376/) (2020)

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

- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [Neural Architecture Search: Two Constant Shared Weights Initialisations](https://mlsanity.com/paper/2302.04406/) (2023)
- [Graph Neural Machine: A New Model for Learning with Tabular Data](https://mlsanity.com/paper/2402.02862/) (2024)
- [MSTAR: Multi-Scale Backbone Architecture Search for Timeseries Classification](https://mlsanity.com/paper/2402.13822/) (2024)

## Abstract (arXiv)

In this work, we propose a novel evolutionary algorithm for neural architecture search, applicable to global search spaces. The algorithm's architectural representation organizes the topology in multiple hierarchical modules, while the design process exploits this representation, in order to explore the search space. We also employ a curation system, which promotes the utilization of well performing sub-structures to subsequent generations. We apply our method to Fashion-MNIST and NAS-Bench101, achieving accuracies of 93.2% and 94.8% respectively in a relatively small number of generations.