In this work, we propose Salient Sparse Federated Learning (SSFL), a
streamlined approach for sparse federated learning with efficient
communication. SSFL identifies a sparse subnetwork prior to training,
leveraging parameter saliency scores computed separately on local client data
in non-IID scenarios, and then aggregated, to determine a global mask. Only the
sparse model weights are communicated each round between the clients and the
server. We validate SSFL's effectiveness using standard non-IID benchmarks,
noting marked improvements in the sparsity--accuracy trade-offs. Finally, we
deploy our method in a real-world federated learning framework and report
improvement in communication time.

我们提出了显著稀疏联合学习（SSFL），一种用于稀疏联合学习并具有高效通信的简化方法。在非独立同分布的情况下，SSFL 在训练之前利用在本地客户端数据上分别计算的参数显著性得分，并进行聚合，以确定全局掩码。在客户端和服务器之间每一轮只传递稀疏模型权重。我们通过标准的非独立同分布基准验证了 SSFL 的有效性，并注意到在稀疏性和准确性权衡方面有显著的改进。最后，我们在实际联合学习框架中部署了我们的方法，并报告了通信时间的改善。