V2V: A Deep Learning Approach to Variable-to-Variable Selection and Translation for Multivariate Time-Varying Data
V2V: A Deep Learning Approach to Variable-to-Variable Selection and Translation for Multivariate Time-Varying Data
复制标题
DOI：
10.1109/tvcg.2020.3030346
复制
发表时间：
2021-02-01
影响因子：
5.2
通讯作者：
Wang, Chaoli
中科院分区：
文献类型：
--
作者：
Han, Jun;Zheng, Hao;Wang, Chaoli
我们提出了V2 V，一种新型的深度学习框架，作为多变量时变数据（MTVD）分析和可视化的变量到变量（V2 V）选择和转换问题的通用解决方案。V2 V利用表示学习算法来识别可转移变量，并利用Kullback-Leibler散度来确定源变量和目标变量。然后，它使用生成对抗网络（GAN）通过对抗、体积和特征损失来学习从源变量到目标变量的映射。V2 V将源变量和目标变量的时间步长对作为训练的输入。一旦训练完毕，它可以在给定源变量的对应时间步长的情况下推断目标变量的不可见时间步长。几个多变量的不同特性的时变数据集被用来证明V2 V的有效性，定量和定性。我们将V2 V与直方图匹配和其他两种深度学习解决方案（Pix 2 Pix和CycleGAN）进行了比较。
We present V2V, a novel deep learning framework, as a general-purpose solution to the variable-to-variable (V2V) selection and translation problem for multivariate time-varying data (MTVD) analysis and visualization. V2V leverages a representation learning algorithm to identify transferable variables and utilizes Kullback-Leibler divergence to determine the source and target variables. It then uses a generative adversarial network (GAN) to learn the mapping from the source variable to the target variable via the adversarial, volumetric, and feature losses. V2V takes the pairs of time steps of the source and target variable as input for training, Once trained, it can infer unseen time steps of the target variable given the corresponding time steps of the source variable. Several multivariate time-varying data sets of different characteristics are used to demonstrate the effectiveness of V2V, both quantitatively and qualitatively. We compare V2V against histogram matching and two other deep learning solutions (Pix2Pix and CycleGAN).