Paletteviz with star-coordinates: An improved method for high-dimensional pareto-optimal front visualization and decision-making
Abstract
Visual representation of a many-objective Pareto-optimal front in four or more dimensional objective space requires a large number of data points. Moreover, choosing a single point from a large set even with certain preference information is problematic, as it causes a large cognitive burden on the part of the decision-makers. Therefore, many-objective optimization and decision-making practitioners have been interested in effective visualization methods to enable them to filter down a large set to a few critical points for further analysis. Most existing visualization methods are borrowed from other data analytics domain and they are too generic to be effective for manycriteria decision making. In this paper, we propose a visualization method, following an earlier concept, using star-coordinate plots for effectively visualizing many-objective trade-off solutions. The proposed method respects some basic topological, geometric and functional decision-making properties of high-dimensional tradeoff points mapped to a three-dimensional space. We demonstrate the use of the proposed method to a number large-dimensional test problems and a 10-objective real-world problem. The use of `Pareto Race' concept from MCDM literature is introduced within the proposed visualization method to demonstrate the ease and advantage of the visualization method.
Authors: Akm Khaled Ahsan Talukder, Kalyanmoy Deb
Published in: IEEE Symposium Series on Computational Intelligence (SSCI) (2020)