# DiCE-Extended: A Robust Approach to Counterfactual Explanations in Machine Learning

arXiv: https://arxiv.org/abs/2504.19027 · HTML: https://mlsanity.com/paper/2504.19027/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 26 Apr 2025.

## Builds on (most cited first, 17 of 17)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Explanations can be manipulated and geometry is to blame](https://mlsanity.com/paper/1906.07983/) (2019)
- [Multi-Objective Counterfactual Explanations](https://mlsanity.com/paper/2004.11165/) (2020)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2102.03322/) (2021)
- [Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contexts](https://mlsanity.com/paper/2201.10295/) (2022)
- [Interpretable Credit Application Predictions With Counterfactual Explanations](https://mlsanity.com/paper/1811.05245/) (2018)
- [ViCE: Visual Counterfactual Explanations for Machine Learning Models](https://mlsanity.com/paper/2003.02428/) (2020)
- [On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbations](https://mlsanity.com/paper/2201.09051/) (2022)
- [ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models](https://mlsanity.com/paper/2110.11960/) (2021)
- [RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model](https://mlsanity.com/paper/2206.00700/) (2022)
- [Achieving Diversity in Counterfactual Explanations: a Review and Discussion](https://mlsanity.com/paper/2305.05840/) (2023)
- [The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning](https://mlsanity.com/paper/2410.09600/) (2024)
- [Transforming In-Vehicle Network Intrusion Detection: VAE-based Knowledge Distillation Meets Explainable AI](https://mlsanity.com/paper/2410.09043/) (2024)
- [Generally-Occurring Model Change for Robust Counterfactual Explanations](https://mlsanity.com/paper/2407.11426/) (2024)
- [LENS-XAI: Redefining Lightweight and Explainable Network Security through Knowledge Distillation and Variational Autoencoders for Scalable Intrusion Detection in Cybersecurity](https://mlsanity.com/paper/2501.00790/) (2025)

## Abstract (arXiv)

Explainable artificial intelligence (XAI) has become increasingly important in decision-critical domains such as healthcare, finance, and law. Counterfactual (CF) explanations, a key approach in XAI, provide users with actionable insights by suggesting minimal modifications to input features that lead to different model outcomes. Despite significant advancements, existing CF generation methods often struggle to balance proximity, diversity, and robustness, limiting their real-world applicability. A widely adopted framework, Diverse Counterfactual Explanations (DiCE), emphasizes diversity but lacks robustness, making CF explanations sensitive to perturbations and domain constraints. To address these challenges, we introduce DiCE-Extended, an enhanced CF explanation framework that integrates multi-objective optimization techniques to improve robustness while maintaining interpretability. Our approach introduces a novel robustness metric based on the Dice-Sorensen coefficient, enabling stability under small input variations. Additionally, we refine CF generation using weighted loss components (lambdap, lambdad, lambdar) to balance proximity, diversity, and robustness. We empirically validate DiCE-Extended on benchmark datasets (COMPAS, Lending Club, German Credit, Adult Income) across multiple ML backends (Scikit-learn, PyTorch, TensorFlow). Results demonstrate improved CF validity, stability, and alignment with decision boundaries compared to standard DiCE-generated explanations. Our findings highlight the potential of DiCE-Extended in generating more reliable and interpretable CFs for high-stakes applications. Future work could explore adaptive optimization techniques and domain-specific constraints to further enhance CF generation in real-world scenarios