<ul><li>FedPaI is a novel efficient federated learning (FL) framework that achieves extreme sparsity by leveraging Pruning at Initialization (PaI).</li><li>FedPaI maximizes model capacity and reduces communication and computation overhead by fixing sparsity patterns at the start of training.</li><li>The framework supports both structured and unstructured pruning, personalized client-side pruning mechanisms, and sparsity-aware server-side aggregation.</li><li>Experimental results show that FedPaI achieves an extreme sparsity level of up to 98% without compromising model accuracy compared to unpruned baselines.</li></ul>

FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization

Discover more