Visual Analytics and Imaging Laboratory (VAI Lab)
Computer Science Department, Stony Brook University, NY
Abstract: Analyzing high-dimensional data and finding hidden patterns is a difficult problem and has attracted numerous research efforts. Automated methods can be useful to some extent but bringing the data analyst into the loop via interactive visual tools can help the discovery process tremendously. An inherent problem in this effort is that humans lack the mental capacity to truly understand spaces exceeding three spatial dimensions. To keep within this limitation, we describe a framework that decomposes a high-dimensional data space into a continuum of generalized 3D subspaces. Analysts can then explore these 3D subspaces individually via the familiar trackball interface while using additional facilities to smoothly transition to adjacent subspaces for expanded space comprehension. Since the number of such subspaces suffers from combinatorial explosion, we provide a set of data-driven subspace selection and navigation tools which can guide users to interesting subspaces and views. A subspace trail map allows users to manage the explored subspaces, keep their bearings, and return to interesting subspaces and views. Both trackball and trail map are each embedded into a word cloud of attribute labels which aid in navigation. We demonstrate our system via several use cases in a diverse set of application areas – cluster analysis and refinement, information discovery, and supervised training of classifiers. We also report on a user study that evaluates the usability of the various interactions our system provides.
Teaser: An actual use case: exploring a high-dimensional sales campaign dataset
The Subspace Voyager interface. It has three main components: the Subspace Explorer (SE), the Subspace Trail Map (STM) and the control panel (bottom left). The SE is coupled with the trackball interface. It not only displays the data as a scatterplot, but it also allows users to visualize the current directions of the projected dimension axis vectors as labels placed outside its circular boundary. The labels are properly sized in terms of the corresponding attribute’s influence on the display. The SE offers various interactions for users to examine the data. The STM holds a set of views (and their parameters) that users may have found interesting during the exploration, embedding them into a word cloud of attributes. Finally, the control panel allows users to set the various parameters and modes in the system.
Video: Watch it to get a quick overview:
Paper: B. Wang, K. Mueller, "The Subspace Voyager: Exploring High-Dimensional Data along a Continuum of Salient 3D Subspaces," IEEE Trans. on Visualization and Computer Graphics, 24(2): 1204-1222, 2018. pdf ppt