Dependency aware feature selection is a simple but effective method proposed in Somol, Petr, Jiří Grim, and Pavel Pudil. "Fast dependency-aware feature selection in very-high-dimensional pattern recognition." 2011 IEEE International Conference on Systems, Man, and Cybernetics. IEEE, 2011.. The method is realated to Shapley values (https://en.wikipedia.org/wiki/Shapley_value) and hence to explanation methods based on this GT concept Kononenko, Igor. "An efficient explanation of individual classifications using game theory." Journal of Machine Learning Research 11.Jan (2010): 1-18.