Selecting and Sharing Multidimensional Projection Algorithms: A Practical View

Abstract

Multidimensional Projection techniques are often used by data analysts for exploring multivariate datasets, but the task of selecting the best technique for the job is not trivial, as there are many candidates and the reasons for picking one over another are usually unclear. On the other hand, researchers developing new techniques can have a hard time comparing their new technique to existing ones and sharing their code in a way that makes it readily available for the public. In this paper, we try to address those issues systematically by analyzing recent surveys in the area, identifying the methods and tools used, and discussing challenges, limitations, and ideas for further work.