Accurate estimation of feature importance faithfulness for tree models
Abstract: In this paper, we consider a perturbation-based metric of predictive faithfulness of feature rankings (or attributions) that we call PGI squared. When applied to decision tree-based regression models, the metric can be computed accurately and efficiently for arbitrary independent feature perturbation distributions. In particular, the computation does not involve Monte Carlo sampling that has been typically used for computing similar metrics and which is inherently prone to inaccuracies. Moreover, we propose a method of ranking features by their importance for the tree model's predictions based on PGI squared. Our experiments indicate that in some respects, the method may identify the globally important features better than the state-of-the-art SHAP explainer
- Openxai: Towards a transparent evaluation of model explanations. Advances in Neural Information Processing Systems, 35:15784–15799, 2022.
- On the robustness of interpretability methods. arXiv preprint arXiv:1806.08049, 2018.
- A survey on the explainability of supervised machine learning. J. Artif. Intell. Res., 70:245–317, 2021.
- The road to explainability is paved with bias: Measuring the fairness of explanations. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pages 1194–1206, 2022.
- Wine Quality. UCI Machine Learning Repository, 2009. DOI: https://doi.org/10.24432/C56S3T.
- Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16. ACM, August 2016.
- ERASER: A benchmark to evaluate rationalized NLP models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, July 5-10, 2020, pages 4443–4458. Association for Computational Linguistics, 2020.
- Fairness via explanation quality: Evaluating disparities in the quality of post hoc explanations. In Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, pages 203–214, 2022.
- A benchmark for interpretability methods in deep neural networks. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 9734–9745, 2019.
- From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell., 2(1):56–67, 2020.
- Synthetic benchmarks for scientific research in explainable machine learning. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual, 2021.
- A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017.
- RISE: randomized input sampling for explanation of black-box models. In British Machine Vision Conference 2018, BMVC 2018, Newcastle, UK, September 3-6, 2018, page 151. BMVA Press, 2018.
- Model agnostic supervised local explanations. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, pages 2520–2529, 2018.
- ”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, San Francisco, CA, USA, August 13-17, 2016, pages 1135–1144. ACM, 2016.
- Luis Torgo. California housing dataset. https://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.html, 2023. Accessed on: October 10, 2023.
- On the (in) fidelity and sensitivity of explanations. Advances in Neural Information Processing Systems, 32, 2019.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.