Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TX-Gen: Multi-Objective Optimization for Sparse Counterfactual Explanations for Time-Series Classification

Qi Huang, Sofoklis Kitharidis, Thomas Bäck, Niki van Stein

TL;DR

TX-Gen is introduced, a novel algorithm for generating counterfactual explanations based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II) that leverages evolutionary multi-objective optimization to find a diverse set of counterfactuals that are both sparse and valid, while maintaining minimal dissimilarity to the original time series.

Abstract

In time-series classification, understanding model decisions is crucial for their application in high-stakes domains such as healthcare and finance. Counterfactual explanations, which provide insights by presenting alternative inputs that change model predictions, offer a promising solution. However, existing methods for generating counterfactual explanations for time-series data often struggle with balancing key objectives like proximity, sparsity, and validity. In this paper, we introduce TX-Gen, a novel algorithm for generating counterfactual explanations based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II). TX-Gen leverages evolutionary multi-objective optimization to find a diverse set of counterfactuals that are both sparse and valid, while maintaining minimal dissimilarity to the original time series. By incorporating a flexible reference-guided mechanism, our method improves the plausibility and interpretability of the counterfactuals without relying on predefined assumptions. Extensive experiments on benchmark datasets demonstrate that TX-Gen outperforms existing methods in generating high-quality counterfactuals, making time-series models more transparent and interpretable.

TX-Gen: Multi-Objective Optimization for Sparse Counterfactual Explanations for Time-Series Classification

TL;DR

TX-Gen is introduced, a novel algorithm for generating counterfactual explanations based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II) that leverages evolutionary multi-objective optimization to find a diverse set of counterfactuals that are both sparse and valid, while maintaining minimal dissimilarity to the original time series.

Abstract

In time-series classification, understanding model decisions is crucial for their application in high-stakes domains such as healthcare and finance. Counterfactual explanations, which provide insights by presenting alternative inputs that change model predictions, offer a promising solution. However, existing methods for generating counterfactual explanations for time-series data often struggle with balancing key objectives like proximity, sparsity, and validity. In this paper, we introduce TX-Gen, a novel algorithm for generating counterfactual explanations based on the Non-dominated Sorting Genetic Algorithm II (NSGA-II). TX-Gen leverages evolutionary multi-objective optimization to find a diverse set of counterfactuals that are both sparse and valid, while maintaining minimal dissimilarity to the original time series. By incorporating a flexible reference-guided mechanism, our method improves the plausibility and interpretability of the counterfactuals without relying on predefined assumptions. Extensive experiments on benchmark datasets demonstrate that TX-Gen outperforms existing methods in generating high-quality counterfactuals, making time-series models more transparent and interpretable.
Paper Structure (22 sections, 3 equations, 2 figures, 6 tables, 5 algorithms)

This paper contains 22 sections, 3 equations, 2 figures, 6 tables, 5 algorithms.

Table of Contents

  1. INTRODUCTION
  2. Contributions
  3. Problem Statement
  4. Goal
  5. BACKGROUND
  6. Evaluation Metrics
  7. Related Work
  8. METHODOLOGY
  9. The framework
  10. Model-based Selection of References
  11. The Objective Functions
  12. Locating the Sequences of Interest
  13. Chromosome Representation
  14. Initialization
  15. Crossover
  16. ...and 7 more sections

Figures (2)

  • Figure 1: In both figures, the length of the to-be-explained time series is $M=40$.
  • Figure 2: Selection of examples of TX-Gen on different datasets and using different classifiers. In each subfigure, the left part shows the distribution of objective values ($F_1$ on the x axis and $F_2$ on the y axis) of the Pareto front. The right part of each figure displays the counterfactual examples and corresponding labels. The time series being explained is highlighted in green, while the counterfactual subsequence of interest (SoIs) are color-coded according to their position on the Pareto front.

Theorems & Definitions (1)

  • Definition 1: Distance in the Classifier