This is something I plan to implement in the future, if people find it useful. Grouping estimators and displaying each group with a different color. This can be used to indicate, for example, which of the methods being compared is the proposed method of a study, or to highlight main baseline estimators. Example:

An idea would be to have hue and hue_order parameters in the critical_difference_diagram function, the first being a Series or dict with same index/keys as the ranks parameter that assigns a group label to each estimator, and hue_order being an iterable with the group names, determining in which order should they be picked to assign a color (inspired by seaborn functionality).