Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

CountARFactuals -- Generating plausible model-agnostic counterfactual explanations with adversarial random forests (2404.03506v1)

Published 4 Apr 2024 in stat.ML and cs.LG

Abstract: Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model's behavior, they hint users towards possible actions and give grounds for contesting decisions. As a crucial factor in achieving these goals, counterfactuals must be plausible, i.e., describing realistic alternative scenarios within the data manifold. This paper leverages a recently developed generative modeling technique -- adversarial random forests (ARFs) -- to efficiently generate plausible counterfactuals in a model-agnostic way. ARFs can serve as a plausibility measure or directly generate counterfactual explanations. Our ARF-based approach surpasses the limitations of existing methods that aim to generate plausible counterfactual explanations: It is easy to train and computationally highly efficient, handles continuous and categorical data naturally, and allows integrating additional desiderata such as sparsity in a straightforward manner.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Jenna Burrell. How the machine ‘thinks’: Understanding opacity in machine learning algorithms. Big Data & Society, 3(1):2053951715622512, 2016.
  2. Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE access, 6:52138–52160, 2018.
  3. Christoph Molnar. Interpretable Machine Learning. 2 edition, 2022.
  4. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harv. JL & Tech., 31:841, 2017.
  5. A survey of algorithmic recourse: Contrastive explanations and consequential recommendations. ACM Computing Surveys, 55(5):1–29, 2022.
  6. Improvement-focused causal recourse (ICR). In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 11847–11855, 2023.
  7. Conceptualising contestability: Perspectives on contesting algorithmic decisions. Proceedings of the ACM on Human-Computer Interaction, 5(CSCW1):1–25, 2021.
  8. Explaining explanations in ai. In Proceedings of the conference on fairness, accountability, and transparency, pages 279–288, 2019.
  9. Multi-objective counterfactual explanations. In International Conference on Parallel Problem Solving from Nature, pages 448–469. Springer, 2020.
  10. Leo Breiman. Statistical modeling: The two cultures (with comments and a rejoinder by the author). Statistical Science, 16(3):199 – 231, 2001.
  11. Riccardo Guidotti. Counterfactual explanations and how to find them: Literature review and benchmarking. Data Mining and Knowledge Discovery, pages 1–55, 2022.
  12. NICE: An algorithm for nearest instance counterfactual explanations. Data Mining and Knowledge Discovery, pages 1–39, 2023.
  13. Towards realistic individual recourse and actionable explanations in black-box decision making systems. arXiv preprint arXiv:1907.09615, 2019.
  14. Preserving causal constraints in counterfactual explanations for machine learning classifiers. arXiv preprint arXiv:1912.03277, 2019.
  15. Learning model-agnostic counterfactual explanations for tabular data. In Proceedings of the web conference 2020, pages 3126–3132, 2020.
  16. Countergan: Generating counterfactuals for real-time recourse and interpretability using residual gans. In Uncertainty in Artificial Intelligence, pages 1488–1497. PMLR, 2022.
  17. Conditional generative models for counterfactual explanations. arXiv preprint arXiv:2101.10123, 2021.
  18. Adversarial random forests for density estimation and generative modeling. In Proceedings of the 26t⁢hsuperscript26𝑡ℎ26^{th}26 start_POSTSUPERSCRIPT italic_t italic_h end_POSTSUPERSCRIPT International Conference on Artificial Intelligence and Statistics, pages 5357–5375. PMLR, 2023.
  19. Timo Freiesleben. The intriguing relation between counterfactual explanations and adversarial examples. Minds and Machines, 32(1):77–109, 2022.
  20. If only we had better counterfactual explanations: Five key deficits to rectify in the evaluation of counterfactual XAI techniques. arXiv preprint arXiv:2103.01035, 2021.
  21. A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence. IEEE Access, 9:11974–12001, 2021.
  22. Counterfactual explanations and algorithmic recourses for machine learning: A review. arXiv preprint arXiv:2010.10596, 2020.
  23. Good counterfactuals and where to find them: A case-based technique for generating counterfactuals for explainable ai (XAI). In Case-Based Reasoning Research and Development: 28th International Conference, ICCBR 2020, Salamanca, Spain, June 8–12, 2020, Proceedings 28, pages 163–178. Springer, 2020.
  24. Dace: Distribution-aware counterfactual explanation by mixed-integer linear optimization. In IJCAI, pages 2855–2862, 2020.
  25. Convex density constraints for computing plausible counterfactual explanations. In Artificial Neural Networks and Machine Learning–ICANN 2020: 29th International Conference on Artificial Neural Networks, Bratislava, Slovakia, September 15–18, 2020, Proceedings, Part I 29, pages 353–365. Springer, 2020.
  26. Counterfactual visual explanations. In International Conference on Machine Learning, pages 2376–2384. PMLR, 2019.
  27. Face: feasible and actionable counterfactual explanations. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pages 344–350, 2020.
  28. John C Gower. A general coefficient of similarity and some of its properties. Biometrics, 27(4):857–871, 1971.
  29. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation, 6(2):182–197, 2002.
  30. Predictive distribution modeling using transformation forests. Journal of Computational and Graphical Statistics, 30(4):1181–1196, March 2021.
  31. Auto-encoding variational bayes. In Proceedings of the 2n⁢dsuperscript2𝑛𝑑2^{nd}2 start_POSTSUPERSCRIPT italic_n italic_d end_POSTSUPERSCRIPT International Conference on Learning Representations, 2014.
  32. Generative adversarial nets. In Advances in Neural Information Processing Systems, volume 27, 2014.
  33. Variational inference with normalizing flows. In Proceedings of the 32t⁢hsuperscript32𝑡ℎ32^{th}32 start_POSTSUPERSCRIPT italic_t italic_h end_POSTSUPERSCRIPT International Conference on Machine Learning, pages 1530–1538. PMLR, 2015.
  34. Denoising diffusion probabilistic models. In Advances in Neural Information Processing Systems, volume 33, pages 6840–6851, 2020.
  35. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30, 2017.
  36. Deep generative modelling: A comparative review of VAEs, GANs, normalizing flows, energy-based and autoregressive models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11):7327–7347, 2021.
  37. David Foster. Generative deep learning: Teaching machines to paint, write, compose, and play. O’Reilly Media, Inc., 2n⁢dsuperscript2𝑛𝑑2^{nd}2 start_POSTSUPERSCRIPT italic_n italic_d end_POSTSUPERSCRIPT edition, 2022.
  38. Deep neural networks and tabular data: A survey. IEEE Transactions on Neural Networks and Learning Systems, 2022.
  39. Why do tree-based models still outperform deep learning on typical tabular data? In Advances in Neural Information Processing Systems, volume 35, pages 507–520, 2022.
  40. Tabular data: Deep learning is not all you need. Information Fusion, 81:84–90, 2022.
  41. Unsupervised learning with random forest predictors. Journal of Computational and Graphical Statistics, 15(1):118–138, 2006.
  42. Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. Journal of Computational and Graphical Statistics, 24(1):44–65, January 2015.
  43. mlbench: Machine learning benchmark problems, 2021. R package version 2.1-3.1.
  44. XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, pages 785–794, New York, NY, USA, 2016. ACM.
  45. counterfactuals: An R package for counterfactual explanation methods, 2023.
  46. Multiobjective optimization using evolutionary algorithms — A comparative case study, page 292–301. Springer Berlin Heidelberg, 1998.
  47. Exploratory analysis of stochastic local search algorithms in biobjective optimization, page 209–222. Springer Berlin Heidelberg, 2010.
  48. On generating trustworthy counterfactual explanations. Information Sciences, 655:119898, 2024.
  49. Coffee Quality Insitute. https://www.coffeeinstitute.org/. Last accessed: 2024-03-12.
  50. Algorithmic recourse: From counterfactual explanations to interventions. In Proceedings of the 2021 ACM conference on fairness, accountability, and transparency, pages 353–362, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Susanne Dandl (12 papers)
  2. Kristin Blesch (5 papers)
  3. Timo Freiesleben (11 papers)
  4. Gunnar König (14 papers)
  5. Jan Kapar (5 papers)
  6. Bernd Bischl (136 papers)
  7. Marvin Wright (4 papers)
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now