Introducing User Feedback-based Counterfactual Explanations (UFCE)
This work addresses the need for more practical and user-centric explanations in machine learning, particularly for applications where interpretability is critical, though it is incremental as it builds on existing CE methods.
The paper tackles the problem of generating counterfactual explanations in XAI by introducing a user feedback-based method (UFCE) that incorporates user constraints to identify minimal modifications in actionable features, resulting in improved proximity, sparsity, and feasibility compared to existing methods.
Machine learning models are widely used in real-world applications. However, their complexity makes it often challenging to interpret the rationale behind their decisions. Counterfactual explanations (CEs) have emerged as a viable solution for generating comprehensible explanations in eXplainable Artificial Intelligence (XAI). CE provides actionable information to users on how to achieve the desired outcome with minimal modifications to the input. However, current CE algorithms usually operate within the entire feature space when optimizing changes to turn over an undesired outcome, overlooking the identification of key contributors to the outcome and disregarding the practicality of the suggested changes. In this study, we introduce a novel methodology, that is named as user feedback-based counterfactual explanation (UFCE), which addresses these limitations and aims to bolster confidence in the provided explanations. UFCE allows for the inclusion of user constraints to determine the smallest modifications in the subset of actionable features while considering feature dependence, and evaluates the practicality of suggested changes using benchmark evaluation metrics. We conducted three experiments with five datasets, demonstrating that UFCE outperforms two well-known CE methods in terms of \textit{proximity}, \textit{sparsity}, and \textit{feasibility}. Reported results indicate that user constraints influence the generation of feasible CEs.