# Federated Neural Architecture Search with Model-Agnostic Meta Learning

arXiv: https://arxiv.org/abs/2504.06457 · HTML: https://mlsanity.com/paper/2504.06457/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## Builds on (most cited first, 25 of 25)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Ditto: Fair and Robust Federated Learning Through Personalization](https://mlsanity.com/paper/2012.04221/) (2020)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [Personalized Federated Learning: A Meta-Learning Approach](https://mlsanity.com/paper/2002.07948/) (2020)
- [FedML: A Research Library and Benchmark for Federated Machine Learning](https://mlsanity.com/paper/2007.13518/) (2020)
- [SNAS: Stochastic Neural Architecture Search](https://mlsanity.com/paper/1812.09926/) (2018)
- [UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory](https://mlsanity.com/paper/1609.02132/) (2016)
- [FedBABU: Towards Enhanced Representation for Federated Image Classification](https://mlsanity.com/paper/2106.06042/) (2021)
- [Federated Meta-Learning with Fast Convergence and Efficient Communication](https://mlsanity.com/paper/1802.07876/) (2018)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Meta-Learning of Neural Architectures for Few-Shot Learning](https://mlsanity.com/paper/1911.11090/) (2019)
- [DSNAS: Direct Neural Architecture Search without Parameter Retraining](https://mlsanity.com/paper/2002.09128/) (2020)
- [MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation](https://mlsanity.com/paper/2003.12238/) (2020)
- [MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning](https://mlsanity.com/paper/2003.14058/) (2020)
- [FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning](https://mlsanity.com/paper/2404.02478/) (2024)

## Abstract (arXiv)

Federated Learning (FL) often struggles with data heterogeneity due to the naturally uneven distribution of user data across devices. Federated Neural Architecture Search (NAS) enables collaborative search for optimal model architectures tailored to heterogeneous data to achieve higher accuracy. However, this process is time-consuming due to extensive search space and retraining. To overcome this, we introduce FedMetaNAS, a framework that integrates meta-learning with NAS within the FL context to expedite the architecture search by pruning the search space and eliminating the retraining stage. Our approach first utilizes the Gumbel-Softmax reparameterization to facilitate relaxation of the mixed operations in the search space. We then refine the local search process by incorporating Model-Agnostic Meta-Learning, where a task-specific learner adapts both weights and architecture parameters (alphas) for individual tasks, while a meta learner adjusts the overall model weights and alphas based on the gradient information from task learners. Following the meta-update, we propose soft pruning using the same trick on search space to gradually sparsify the architecture, ensuring that the performance of the chosen architecture remains robust after pruning which allows for immediate use of the model without retraining. Experimental evaluations demonstrate that FedMetaNAS significantly accelerates the search process by more than 50% with higher accuracy compared to FedNAS.