HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters
HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters
复制标题
DOI：
10.1111/cgf.14531
复制
发表时间：
2021-06
影响因子：
2.5
通讯作者：
G. Appleby;M. Espadoto;Rui Chen;Sam Goree;A. Telea;Erik W. Anderson;Remco Chang
中科院分区：
文献类型：
--
作者：
G. Appleby;M. Espadoto;Rui Chen;Sam Goree;A. Telea;Erik W. Anderson;Remco Chang
像t-SNE或UMAP这样的投影算法对于高维数据的可视化是有用的，但它们依赖于必须仔细调整的超参数。不幸的是，由于这种方法的随机性，迭代地重新计算投影以找到最佳超参数值是计算密集且不直观的。在本文中，我们提出了HyperNP，这是一种可扩展的方法，允许通过训练神经网络近似来实时交互地探索投影方法。超NP模型可以在人们想要研究的全部数据实例和超参数配置的一小部分上进行训练，并且可以以交互速度计算新数据和超参数的预测。超NP模型体积紧凑，计算速度快，因此可以嵌入到轻量级可视化系统中。我们从性能和速度两个方面评估了HyperNP在三个数据集上的性能。结果表明，HyperNP模型是准确的、可扩展的、交互式的，并且适合在现实世界中使用。
Projection algorithms such as t‐SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperparameters which must be tuned carefully. Unfortunately, iteratively recomputing projections to find the optimal hyperparameter values is computationally intensive and unintuitive due to the stochastic nature of such methods. In this paper we propose HyperNP, a scalable method that allows for real‐time interactive hyperparameter exploration of projection methods by training neural network approximations. A HyperNP model can be trained on a fraction of the total data instances and hyperparameter configurations that one would like to investigate and can compute projections for new data and hyperparameters at interactive speeds. HyperNP models are compact in size and fast to compute, thus allowing them to be embedded in lightweight visualization systems. We evaluate the performance of HyperNP across three datasets in terms of performance and speed. The results suggest that HyperNP models are accurate, scalable, interactive, and appropriate for use in real‐world settings.