Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Info-CELS: Informative Saliency Map Guided Counterfactual Explanation

Peiyu Li, Omar Bahri, Pouya Hosseinzadeh, Soukaïna Filali Boubrahimi, Shah Muhammad Hamdi

TL;DR

The proposed method addresses this limitation by removing mask normalization to provide more informative and valid counterfactual explanations, and outperforms the CELS model, achieving higher validity and producing more informative explanations.

Abstract

As the demand for interpretable machine learning approaches continues to grow, there is an increasing necessity for human involvement in providing informative explanations for model decisions. This is necessary for building trust and transparency in AI-based systems, leading to the emergence of the Explainable Artificial Intelligence (XAI) field. Recently, a novel counterfactual explanation model, CELS, has been introduced. CELS learns a saliency map for the interest of an instance and generates a counterfactual explanation guided by the learned saliency map. While CELS represents the first attempt to exploit learned saliency maps not only to provide intuitive explanations for the reason behind the decision made by the time series classifier but also to explore post hoc counterfactual explanations, it exhibits limitations in terms of high validity for the sake of ensuring high proximity and sparsity. In this paper, we present an enhanced approach that builds upon CELS. While the original model achieved promising results in terms of sparsity and proximity, it faced limitations in validity. Our proposed method addresses this limitation by removing mask normalization to provide more informative and valid counterfactual explanations. Through extensive experimentation on datasets from various domains, we demonstrate that our approach outperforms the CELS model, achieving higher validity and producing more informative explanations.

Info-CELS: Informative Saliency Map Guided Counterfactual Explanation

TL;DR

The proposed method addresses this limitation by removing mask normalization to provide more informative and valid counterfactual explanations, and outperforms the CELS model, achieving higher validity and producing more informative explanations.

Abstract

As the demand for interpretable machine learning approaches continues to grow, there is an increasing necessity for human involvement in providing informative explanations for model decisions. This is necessary for building trust and transparency in AI-based systems, leading to the emergence of the Explainable Artificial Intelligence (XAI) field. Recently, a novel counterfactual explanation model, CELS, has been introduced. CELS learns a saliency map for the interest of an instance and generates a counterfactual explanation guided by the learned saliency map. While CELS represents the first attempt to exploit learned saliency maps not only to provide intuitive explanations for the reason behind the decision made by the time series classifier but also to explore post hoc counterfactual explanations, it exhibits limitations in terms of high validity for the sake of ensuring high proximity and sparsity. In this paper, we present an enhanced approach that builds upon CELS. While the original model achieved promising results in terms of sparsity and proximity, it faced limitations in validity. Our proposed method addresses this limitation by removing mask normalization to provide more informative and valid counterfactual explanations. Through extensive experimentation on datasets from various domains, we demonstrate that our approach outperforms the CELS model, achieving higher validity and producing more informative explanations.

Paper Structure

This paper contains 19 sections, 10 equations, 5 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. Problem Statement
  4. Optimal properties for a good counterfactual explanation
  5. Background Works: CELS
  6. Replacement Strategy: Nearest Unlike Neighbor (NUN)
  7. Counterfactual Perturbation
  8. Learning Explanation
  9. Informative CELS (Info-CELS)
  10. Experimental Study
  11. Baseline Methods
  12. Implementation Details
  13. Evaluation metrics
  14. Evaluation results
  15. Validity evaluation:
  16. ...and 4 more sections

Figures (5)

  • Figure 1: Counterfactual explanation for time series data via learned saliency maps (CELS)
  • Figure 2: Counterfactual explanations obtained from CElS and Info-CELS for the ECG200 and GunPoint datasets. (The x-axis in each figure represents the time steps, indicating the progression of time in the time series data. The y-axis denotes the values corresponding to each time step, showing the changes in the data over time. Below the figure, the 1-dimensional saliency map highlights the importance scores for each time step, ranging between 0 and 1. A score of 1 means the time step is most influential in the model's decision-making process.)
  • Figure 3: Sparsity (the higher the better) and L1 distance (the lower the better) comparison of the CF explanations generated by ALIBI, NG, SG, CELS, and Info-CELS (All the reported results are the average value over the counterfactual set)
  • Figure 4: Different $\lambda$ values
  • Figure 5: Different $\lambda$ values