CAREER: Design Decision Patterns for Visualizing Multivariate Graphs

University Of Utah, Salt Lake City UT

Investigators

Abstract

Multivariate graphs, or datasets that link together entities that are associated with multiple different variables, occur in a broad range of problems. For example, the dataset could be geospatial locations that include socio-economic statistics, linked together through a public transportation system. These multivariate graphs are notoriously difficult to visualize because the number of data variables exceeds the number of available visual cues - these cues include color, size, position, etc. The goal of this project is to establish a set of validated and generalizable techniques for visualizing and interacting with multivariate graphs. Three target application areas will drive the investigations: one in cancer biology, a second in urban transportation, and a third in particle physics. These areas were chosen to represent a wide spectrum of possible applications in which multivariate graphs play a central role, thus fostering generalizable results. The multidisciplinary nature of the research and the close collaboration with domain experts in our target application areas will provide a unique educational environment for undergraduate and graduate students, while also broadening the participation in computer science beyond traditional boundaries. This is the first systematic, problem-driven effort to consider the visualization of multivariate graphs using a diverse set of application areas, with the goal of developing a generalizable set of techniques and principles for supporting a broad range of visualization and data analysis tasks. The research will be conducted with domain experts using a design study methodology, which is a deeply collaborative and user-centered approach to visualization research. The primary impact of this work will be validated visualization design decision patterns for effective visual representation and user-driven exploration of complex multivariate graphs, resulting in a more comprehensive foundation of techniques for visualizing this increasingly important data type. The resulting design decision patterns will support ongoing research and discovery in our target application areas, as well generalize to a broad class of real-world problems. Furthermore, these patterns will form the foundation of software tools for visualizing multivariate graphs that effectively support exploration and sense-making of these complex data types by taking into account the varied relationships embedded within. Results and software will be disseminated to both the research communities of our target application areas, but also more broadly through the project website at http://mvgraphs.sci.utah.edu.