Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Local and Regional Counterfactual Rules: Summarized and Robust Recourses (2209.14568v3)

Published 29 Sep 2022 in stat.ML and cs.LG

Abstract: Counterfactual Explanations (CE) face several unresolved challenges, such as ensuring stability, synthesizing multiple CEs, and providing plausibility and sparsity guarantees. From a more practical point of view, recent studies [Pawelczyk et al., 2022] show that the prescribed counterfactual recourses are often not implemented exactly by individuals and demonstrate that most state-of-the-art CE algorithms are very likely to fail in this noisy environment. To address these issues, we propose a probabilistic framework that gives a sparse local counterfactual rule for each observation, providing rules that give a range of values capable of changing decisions with high probability. These rules serve as a summary of diverse counterfactual explanations and yield robust recourses. We further aggregate these local rules into a regional counterfactual rule, identifying shared recourses for subgroups of the data. Our local and regional rules are derived from the Random Forest algorithm, which offers statistical guarantees and fidelity to data distribution by selecting recourses in high-density regions. Moreover, our rules are sparse as we first select the smallest set of variables having a high probability of changing the decision. We have conducted experiments to validate the effectiveness of our counterfactual rules in comparison to standard CE and recent similar attempts. Our methods are available as a Python package.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Consistent sufficient explanations and minimal local rules for explaining regression and classification models. arXiv preprint arXiv:2111.04658, 2021.
  2. Iterative random forests to discover predictive and stable high-order interactions. Proceedings of the National Academy of Sciences, 115(8):1943–1948, 2018.
  3. Shaff: Fast and consistent shapley effect estimates via random forests. arXiv preprint arXiv:2105.11724, 2021a.
  4. Interpretable random forests via rule extraction. In International Conference on Artificial Intelligence and Statistics, pp.  937–945. PMLR, 2021b.
  5. Mda for random forests: inconsistency, and a practical solution via the sobol-mda. arXiv preprint arXiv:2102.13347, 2021c.
  6. On the layered nearest neighbour estimate, the bagged nearest neighbour estimate and the random forest method in regression and classification. Journal of Multivariate Analysis, 101(10):2499–2518, 2010. ISSN 0047-259X. doi: https://doi.org/10.1016/j.jmva.2010.06.019. URL https://www.sciencedirect.com/science/article/pii/S0047259X10001387.
  7. Fliptest: fairness testing via optimal transport. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp.  111–121, 2020.
  8. Breiman, L. Some infinity theory for predictor ensembles. Technical report, Citeseer, 2000.
  9. Classification and regression trees. wadsworth int. Group, 37(15):237–251, 1984.
  10. Counterfactual explanations for oblique decision trees: Exact, efficient algorithms. In Proceedings of the AAAI conference on artificial intelligence, volume 35, pp.  6903–6911, 2021.
  11. CDC. National health and nutrition examination survey, 1999-2022. URL https://wwwn.cdc.gov/Nchs/Nhanes/Default.aspx.
  12. Counterfactuals and causability in explainable artificial intelligence: Theory, algorithms, and applications. Information Fusion, 81:59–83, 2022. ISSN 1566-2535. doi: https://doi.org/10.1016/j.inffus.2021.11.003. URL https://www.sciencedirect.com/science/article/pii/S1566253521002281.
  13. Transport-based counterfactual models. arXiv preprint arXiv:2108.13025, 2021.
  14. Wasserstein random forests and applications in heterogeneous treatment effects. In International Conference on Artificial Intelligence and Statistics, pp.  1729–1737. PMLR, 2021.
  15. FICO. Fico. explainable machine learning challenge, 2018. URL https://community.fico.com/s/explainable-machine-learning-challenge.
  16. Extremely randomized trees. Machine learning, 63:3–42, 2006.
  17. Your classifier is secretly an energy based model and you should treat it like one. In International Conference on Learning Representations, 2020.
  18. Why do tree-based models still outperform deep learning on typical tabular data? In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2022.
  19. Simulated annealing: a review and a new scheme. pp.  101–105, 07 2021. doi: 10.1109/SSP49050.2021.9513782.
  20. Random survival forests. The annals of applied statistics, 2(3):841–860, 2008.
  21. Heterogeneous treatment effect based random forest: Hterf. 2023.
  22. Kaggle. Pima indians diabetes database, 2016. URL https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database.
  23. Counterfactual explanation trees: Transparent and consistent actionable recourse with decision trees. In Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:1846-1870, 2022.
  24. A survey of algorithmic recourse: definitions, formulations, solutions, and prospects. CoRR, abs/2010.04050, 2020a. URL https://arxiv.org/abs/2010.04050.
  25. Model-agnostic counterfactual explanations for consequential decisions. ArXiv, abs/1905.11190, 2020b.
  26. Sparse spatial autoregressions. Statistics, Probability Letters, 33(3):291–297, 1997. ISSN 0167-7152. doi: https://doi.org/10.1016/S0167-7152(96)00140-X. URL https://www.sciencedirect.com/science/article/pii/S016771529600140X.
  27. Rethinking explainability as a dialogue: A practitioner’s perspective. CoRR, abs/2202.01875, 2022. URL https://arxiv.org/abs/2202.01875.
  28. A tutorial on energy-based learning. 01 2006.
  29. Global counterfactual explanations: Investigations, implementations and improvements, 2022. URL https://arxiv.org/abs/2204.06917.
  30. Random forests and adaptive nearest neighbors. Journal of the American Statistical Association, 101(474):578–590, 2006.
  31. Isolation forest. In 2008 eighth ieee international conference on data mining, pp.  413–422. IEEE, 2008.
  32. Loh, W.-Y. Classification and regression trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1, 2011.
  33. Interpretable counterfactual explanations guided by prototypes. CoRR, abs/1907.02584, 2019. URL http://arxiv.org/abs/1907.02584.
  34. Focus: Flexible optimizable counterfactual explanations for tree ensembles. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pp.  5313–5322, 2022.
  35. From local explanations to global understanding with explainable ai for trees. Nature Machine Intelligence, 2(1):2522–5839, 2020.
  36. Quantile regression forests. Journal of Machine Learning Research, 7(6), 2006.
  37. Molnar, C. Interpretable Machine Learning. 2 edition, 2022. URL https://christophm.github.io/interpretable-ml-book.
  38. Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, FAT* ’20, pp.  607–617, New York, NY, USA, 2020. Association for Computing Machinery. ISBN 9781450369367. doi: 10.1145/3351095.3372850. URL https://doi.org/10.1145/3351095.3372850.
  39. Optimal counterfactual explanations in tree ensembles. CoRR, abs/2106.06631, 2021. URL https://arxiv.org/abs/2106.06631.
  40. The synthetic data vault. In 2016 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp.  399–410, Oct 2016. doi: 10.1109/DSAA.2016.49.
  41. Learning model-agnostic counterfactual explanations for tabular data. In Proceedings of the web conference 2020, pp.  3126–3132, 2020.
  42. Carla: A python library to benchmark algorithmic recourse and counterfactual explanation algorithms, 2021.
  43. Algorithmic recourse in the face of noisy human responses, 2022. URL https://arxiv.org/abs/2203.06768.
  44. FACE: feasible and actionable counterfactual explanations. CoRR, abs/1909.09369, 2019. URL http://arxiv.org/abs/1909.09369.
  45. Beyond individualized recourse: Interpretable and interactive summaries of actionable recourses. Advances in Neural Information Processing Systems, 33:12187–12198, 2020.
  46. ” why should i trust you?” explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp.  1135–1144, 2016.
  47. Russell, C. Efficient search for diverse coherent explanations. In Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* ’19, pp.  20–28, New York, NY, USA, 2019. Association for Computing Machinery. ISBN 9781450361255. doi: 10.1145/3287560.3287569. URL https://doi.org/10.1145/3287560.3287569.
  48. Scornet, E. Random forests and kernel methods. IEEE Transactions on Information Theory, 62(3):1485–1500, 2016.
  49. Interpretable predictions of tree-based ensembles via actionable feature tweaking. In Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining, pp.  465–474, 2017.
  50. Actionable recourse in linear classification. Proceedings of the Conference on Fairness, Accountability, and Transparency, 2019.
  51. Counterfactual explanations for machine learning: A review. CoRR, abs/2010.10596, 2020. URL https://arxiv.org/abs/2010.10596.
  52. Counterfactual explanations without opening the black box: Automated decisions and the gdpr. Cybersecurity, 2017.
  53. Estimation and inference of heterogeneous treatment effects using random forests, 2017.
  54. Washington, A. L. How to argue with an algorithm: Lessons from the compas-propublica debate. Colo. Tech. LJ, 17:131, 2018.
  55. Modeling tabular data using conditional gan. In NeurIPS, 2019.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Salim I. Amoukou (7 papers)
  2. Nicolas J. B Brunel (3 papers)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets