# Counterfactual Explanations for Clustering Models

arXiv: https://arxiv.org/abs/2409.12632 · HTML: https://mlsanity.com/paper/2409.12632/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 39 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Builds on (most cited first, 9 of 9)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [FACE: Feasible and Actionable Counterfactual Explanations](https://mlsanity.com/paper/1909.09369/) (2019)
- [Simple random search provides a competitive approach to reinforcement learning](https://mlsanity.com/paper/1803.07055/) (2018)
- [A Comprehensive Survey on Deep Clustering: Taxonomy, Challenges, and Future Directions](https://mlsanity.com/paper/2206.07579/) (2022)
- [Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning](https://mlsanity.com/paper/2101.12446/) (2021)
- [Explainability Is in the Mind of the Beholder: Establishing the Foundations of Explainable Artificial Intelligence](https://mlsanity.com/paper/2112.14466/) (2021)
- [Navigating Explanatory Multiverse Through Counterfactual Path Geometry](https://mlsanity.com/paper/2306.02786/) (2023)
- [Algorithm-Agnostic Explainability for Unsupervised Clustering](https://mlsanity.com/paper/2105.08053/) (2021)

## Built on by (most cited first, 1 of 1)

- [Counterfactual Explanations for k-means and Gaussian Clustering](https://mlsanity.com/paper/2501.10234/) (2025)

## Abstract (arXiv)

Clustering algorithms rely on complex optimisation processes that may be difficult to comprehend, especially for individuals who lack technical expertise. While many explainable artificial intelligence techniques exist for supervised machine learning, unsupervised learning -- and clustering in particular -- has been largely neglected. To complicate matters further, the notion of a ``true'' cluster is inherently challenging to define. These facets of unsupervised learning and its explainability make it difficult to foster trust in such methods and curtail their adoption. To address these challenges, we propose a new, model-agnostic technique for explaining clustering algorithms with counterfactual statements. Our approach relies on a novel soft-scoring method that captures the spatial information utilised by clustering models. It builds upon a state-of-the-art Bayesian counterfactual generator for supervised learning to deliver high-quality explanations. We evaluate its performance on five datasets and two clustering algorithms, and demonstrate that introducing soft scores to guide counterfactual search significantly improves the results.