论文标题
通过联合学习的培训语音识别模型：质量/成本框架
Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework
论文作者
论文摘要
我们建议使用联合学习（分散的设备学习范式）来培训语音识别模型。通过以每个用户的方式进行培训时期，联邦学习必须征收处理非IID数据分布的成本，这些数据分布有望对受过训练的模型的质量产生负面影响。我们提出了一个框架，可以通过这种框架来改变非IID的程度，因此说明了模型质量与联合培训的计算成本之间的权衡，我们通过新颖的指标捕获了模型质量。最后，我们证明了高参数优化和适当使用变异噪声足以补偿非IID分布的质量影响，同时降低了成本。
We propose using federated learning, a decentralized on-device learning paradigm, to train speech recognition models. By performing epochs of training on a per-user basis, federated learning must incur the cost of dealing with non-IID data distributions, which are expected to negatively affect the quality of the trained model. We propose a framework by which the degree of non-IID-ness can be varied, consequently illustrating a trade-off between model quality and the computational cost of federated training, which we capture through a novel metric. Finally, we demonstrate that hyper-parameter optimization and appropriate use of variational noise are sufficient to compensate for the quality impact of non-IID distributions, while decreasing the cost.
