Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Introducing User Feedback-based Counterfactual Explanations (UFCE)

Muhammad Suffian, Jose M. Alonso-Moral, Alessandro Bogliolo

TL;DR

A novel methodology, that is named as user feedback-based counterfactual explanation (UFCE), which addresses limitations and aims to bolster confidence in the provided explanations, and indicates that user constraints influence the generation of feasible CEs.

Abstract

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.

Introducing User Feedback-based Counterfactual Explanations (UFCE)

TL;DR

A novel methodology, that is named as user feedback-based counterfactual explanation (UFCE), which addresses limitations and aims to bolster confidence in the provided explanations, and indicates that user constraints influence the generation of feasible CEs.

Abstract

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.
Paper Structure (21 sections, 5 equations, 5 figures, 7 tables, 5 algorithms)

This paper contains 21 sections, 5 equations, 5 figures, 7 tables, 5 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Preliminaries
  4. Expressions and Terms
  5. Problem Statement
  6. Evaluation metrics for Counterfactual Explanations
  7. The counterfactual generation pipeline
  8. User Preferences
  9. Mutual Information of features
  10. Nearest Neighbourhood (NN)
  11. Perturbations
  12. Algorithmic Details
  13. Experiments and Results
  14. Experimental Settings
  15. Data sets
  16. ...and 6 more sections

Figures (5)

  • Figure 1: Example of decision surface with counterfactual instance space in the neighbourhood of test instance $x$. The yellow, black, and green dots ($z_1$, $z_2$, $z_3$, $z_4$, $z_5$) are the counterfactual instances: where $z_3$ is invalid; $z_1$, $z_2$, and $z_4$ are valid and actionable; and $z_5$ is valid but not actionable due to not adhering to user defined feature range for Mortgage (assume Bank loan data).
  • Figure 2: Counterfactual explanation generation pipeline of UFCE.
  • Figure 3: (RQ1) Performance of CE methods for different evaluation metrics (with error bar of st.dev).
  • Figure 4: (RQ2) Random user-preferences for CE generation: The bar plots depict the evaluation results for different evaluation metrics (with error bar of st.dev).
  • Figure 5: (RQ3) Comparative results for CE generation on multiple datasets: The bar plots depict the evaluation results for different evaluation metrics (with error bar of st.dev).