EiFFFeL: Enforcing Fairness in Forests by Flipping Leaves
This addresses fairness issues in socially sensitive systems, but it is incremental as it builds on existing tree-based post-processing strategies.
The paper tackles the problem of ensuring fairness in machine learning decisions by proposing EiFFFeL, a post-processing method that flips leaves in decision trees to enforce group fairness, achieving a user-defined fairness degree with minimal accuracy loss.
Nowadays Machine Learning (ML) techniques are extensively adopted in many socially sensitive systems, thus requiring to carefully study the fairness of the decisions taken by such systems. Many approaches have been proposed to address and to make sure there is no bias against individuals or specific groups which might originally come from biased training datasets or algorithm design. In this regard, we propose a fairness enforcing approach called EiFFFeL:Enforcing Fairness in Forests by Flipping Leaves which exploits tree-based or leaf-based post-processing strategies to relabel leaves of selected decision trees of a given forest. Experimental results show that our approach achieves a user defined group fairness degree without losing a significant amount of accuracy.