Distributed learning of deep neural network over multiple agents
Distributed learning of deep neural network over multiple agents
复制标题
DOI：
10.1016/j.jnca.2018.05.003
复制
发表时间：
2018-08-15
影响因子：
8.7
通讯作者：
Raskar, Ramesh
中科院分区：
文献类型：
--
作者：
Gupta, Otkrist;Raskar, Ramesh
在医疗保健和金融等领域，标记数据和计算资源的短缺是开发机器学习算法时的一个关键问题。为了解决基于神经网络的系统的训练和部署中标记数据稀缺的问题，我们提出了一种新技术来在多个数据源上训练深度神经网络。我们的方法允许使用来自多个实体的数据以分布式方式训练深度神经网络。我们在现有数据集上评估我们的算法，并表明它获得的性能类似于在单台机器上训练的常规神经网络。我们进一步扩展它，在使用少量标记样本进行训练时纳入半监督学习，并分析可能出现的任何安全问题。当原始数据无法直接共享时，我们的算法为数据敏感应用中深度神经网络的分布式训练铺平了道路。
In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of neural network-based systems, we propose a new technique to train deep neural networks over several data sources. Our method allows for deep neural networks to be trained using data from multiple entities in a distributed fashion. We evaluate our algorithm on existing datasets and show that it obtains performance which is similar to a regular neural network trained on a single machine. We further extend it to incorporate semi-supervised learning when training with few labeled samples, and analyze any security concerns that may arise. Our algorithm paves the way for distributed training of deep neural networks in data sensitive applications when raw data may not be shared directly.