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.
翻译:我们建议采用联邦化学习这一分散化的在线学习模式来培训语音识别模式。通过以用户为单位开展不同阶段的培训,联邦化学习必须承担处理非国际开发数据传播的费用,预计这将对培训模式的质量产生不利影响。我们建议了一个框架,通过该框架可以改变非国际开发程度,从而说明在模式质量和联邦化培训计算成本之间取舍,我们通过新的衡量标准加以捕捉。 最后,我们证明超参数优化和适当使用变异噪音足以补偿非国际开发数据传播的质量影响,同时降低成本。