Visual Neural Decomposition to Explain Multivariate Data Sets
This addresses the problem for data analysts and engineers by providing a scalable visualization tool for high-dimensional data analysis, though it appears incremental as it builds on existing neural network methods.
The paper tackles the challenge of visualizing correlations between many input variables and a target variable in multivariate datasets, proposing a neural network-based visual model with a new regularization term to improve interpretability, and demonstrates its utility on artificial and real-world data.
Investigating relationships between variables in multi-dimensional data sets is a common task for data analysts and engineers. More specifically, it is often valuable to understand which ranges of which input variables lead to particular values of a given target variable. Unfortunately, with an increasing number of independent variables, this process may become cumbersome and time-consuming due to the many possible combinations that have to be explored. In this paper, we propose a novel approach to visualize correlations between input variables and a target output variable that scales to hundreds of variables. We developed a visual model based on neural networks that can be explored in a guided way to help analysts find and understand such correlations. First, we train a neural network to predict the target from the input variables. Then, we visualize the inner workings of the resulting model to help understand relations within the data set. We further introduce a new regularization term for the backpropagation algorithm that encourages the neural network to learn representations that are easier to interpret visually. We apply our method to artificial and real-world data sets to show its utility.