# MANAS: Multi-Agent Neural Architecture Search

arXiv: https://arxiv.org/abs/1909.01051 · HTML: https://mlsanity.com/paper/1909.01051/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2019.

## Built on by (most cited first, 10 of 10)

- [DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture](https://mlsanity.com/paper/2109.05765/) (2021)
- [Approximate Neural Architecture Search via Operation Distribution Learning](https://mlsanity.com/paper/2111.04670/) (2021)
- [OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators](https://mlsanity.com/paper/2312.09411/) (2023)
- [OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strength](https://mlsanity.com/paper/2409.14433/) (2024)
- [Guided Evolution for Neural Architecture Search](https://mlsanity.com/paper/2110.15232/) (2021)
- [AUTOKD: Automatic Knowledge Distillation Into A Student Architecture Family](https://mlsanity.com/paper/2111.03555/) (2021)
- [Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importance](https://mlsanity.com/paper/2303.16938/) (2023)
- [Guided Evolutionary Neural Architecture Search With Efficient Performance Estimation](https://mlsanity.com/paper/2208.06475/) (2022)
- [Fruit Classification System with Deep Learning and Neural Architecture Search](https://mlsanity.com/paper/2406.01869/) (2024)
- [PaRT: Parallel Learning Towards Robust and Transparent AI](https://mlsanity.com/paper/2201.09534/) (2022)

## Abstract (arXiv)

The Neural Architecture Search (NAS) problem is typically formulated as a graph search problem where the goal is to learn the optimal operations over edges in order to maximise a graph-level global objective. Due to the large architecture parameter space, efficiency is a key bottleneck preventing NAS from its practical use. In this paper, we address the issue by framing NAS as a multi-agent problem where agents control a subset of the network and coordinate to reach optimal architectures. We provide two distinct lightweight implementations, with reduced memory requirements (1/8th of state-of-the-art), and performances above those of much more computationally expensive methods. Theoretically, we demonstrate vanishing regrets of the form O(sqrt(T)), with T being the total number of rounds. Finally, aware that random search is an, often ignored, effective baseline we perform additional experiments on 3 alternative datasets and 2 network configurations, and achieve favourable results in comparison.