To improve federated training of neural networks, we develop FedSparsify, a sparsification strategy based on progressive weight magnitude pruning. Our method has several benefits. First, since the size of the network becomes increasingly smaller, computation and communication costs during training are reduced. Second, the models are incrementally constrained to a smaller set of parameters, which facilitates alignment/merging of the local models and improved learning performance at high sparsification rates. Third, the final sparsified model is significantly smaller, which improves inference efficiency and optimizes operations latency during encrypted communication. We show experimentally that FedSparsify learns a subnetwork of both high sparsity and learning performance. Our sparse models can reach a tenth of the size of the original model with the same or better accuracy compared to existing pruning and nonpruning baselines.
翻译:为了改进对神经网络的联盟培训,我们开发FedSparize(FedSparization),这是基于累进重量级的宽度调整战略。我们的方法有几个好处。首先,由于网络的规模越来越小,培训过程中的计算和通信成本也越来越小。第二,模型逐渐被限制在一套较小的参数上,这有利于当地模型的调整/合并,以及高的加压率提高学习成绩。第三,最后的加压模型要小得多,这提高了推论效率,优化了加密通信中的操作耐久性。我们实验性地显示,FedSparize学会了高度宽度和学习性能的子网络。我们稀有的模型可以达到原始模型的十分之一,与现有的裁剪和不修的基线相同或更精确。