<ul><li>Federated Neural Architecture Search (NAS) enables collaborative search for optimal model architectures tailored to heterogeneous data to achieve higher accuracy.</li><li>FedMetaNAS is a framework that integrates meta-learning with NAS in the context of Federated Learning (FL) to accelerate architecture search by pruning the search space and eliminating the retraining stage.</li><li>It utilizes the Gumbel-Softmax reparameterization and Model-Agnostic Meta-Learning techniques to facilitate relaxation of mixed operations and adapt weights and architecture parameters for individual tasks.</li><li>Experimental evaluations demonstrate that FedMetaNAS significantly accelerates the search process by more than 50% with higher accuracy compared to FedNAS.</li></ul>

Federated Neural Architecture Search with Model-Agnostic Meta Learning

Discover more