Cieran: Designing Sequential Colormaps via In-Situ Active Preference Learning
This addresses the challenge for data analysts, particularly novices in color design, to quickly find aesthetically pleasing colormaps tailored to their data, though it is incremental in applying existing active learning methods to visualization design.
The paper tackled the problem of designing quality sequential colormaps for data visualization by introducing Cieran, a tool that uses active preference learning to rank and create colormaps based on user preferences, and found it effectively modeled preferences and generated new designs in an evaluation with twelve scientists.
Quality colormaps can help communicate important data patterns. However, finding an aesthetically pleasing colormap that looks "just right" for a given scenario requires significant design and technical expertise. We introduce Cieran, a tool that allows any data analyst to rapidly find quality colormaps while designing charts within Jupyter Notebooks. Our system employs an active preference learning paradigm to rank expert-designed colormaps and create new ones from pairwise comparisons, allowing analysts who are novices in color design to tailor colormaps to their data context. We accomplish this by treating colormap design as a path planning problem through the CIELAB colorspace with a context-specific reward model. In an evaluation with twelve scientists, we found that Cieran effectively modeled user preferences to rank colormaps and leveraged this model to create new quality designs. Our work shows the potential of active preference learning for supporting efficient visualization design optimization.