2000 character limit reached
Unifying Perspectives: Plausible Counterfactual Explanations on Global, Group-wise, and Local Levels
Published 27 May 2024 in cs.LG, cs.AI, and stat.ME | (2405.17642v2)
Abstract: The growing complexity of AI systems has intensified the need for transparency through Explainable AI (XAI). Counterfactual explanations (CFs) offer actionable "what-if" scenarios on three levels: Local CFs providing instance-specific insights, Global CFs addressing broader trends, and Group-wise CFs (GWCFs) striking a balance and revealing patterns within cohesive groups. Despite the availability of methods for each granularity level, the field lacks a unified method that integrates these complementary approaches. We address this limitation by proposing a gradient-based optimization method for differentiable models that generates Local, Global, and Group-wise Counterfactual Explanations in a unified manner. We especially enhance GWCF generation by combining instance grouping and counterfactual generation into a single efficient process, replacing traditional two-step methods. Moreover, to ensure trustworthiness, we innovatively introduce the integration of plausibility criteria into the GWCF domain, making explanations both valid and realistic. Our results demonstrate the method's effectiveness in balancing validity, proximity, and plausibility while optimizing group granularity, with practical utility validated through practical use cases.
- Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6:52138–52160.
- 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, volume 12396 of Lecture Notes in Computer Science, pages 353–365. Springer.
- Explanations based on the missing: Towards contrastive explanations with pertinent negatives. 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 590–601.
- NICE: non-linear independent components estimation. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Workshop Track Proceedings.
- Density estimation using real NVP. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.
- Learning groupwise explanations for black-box models. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, pages 2396–2402. ijcai.org.
- European union regulations on algorithmic decision-making and a "right to explanation". AI Mag., 38(3):50–57.
- Guidotti, R. (2022). Counterfactual explanations and how to find them: literature review and benchmarking. Data Mining and Knowledge Discovery, pages 1–55.
- DACE: distribution-aware counterfactual explanation by mixed-integer linear optimization. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI 2020, pages 2855–2862. ijcai.org.
- Counterfactual explanation trees: Transparent and consistent actionable recourse with decision trees. In International Conference on Artificial Intelligence and Statistics, AISTATS 2022, 28-30 March 2022, Virtual Event, volume 151 of Proceedings of Machine Learning Research, pages 1846–1870. PMLR.
- A survey of algorithmic recourse: definitions, formulations, solutions, and prospects. CoRR, abs/2010.04050.
- If only we had better counterfactual explanations: Five key deficits to rectify in the evaluation of counterfactual XAI techniques. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021.
- Global counterfactual explanations: Investigations, implementations and improvements. CoRR, abs/2204.06917.
- GLOBE-CE: A translation based approach for global counterfactual explanations. In Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., and Scarlett, J., editors, International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA, volume 202 of Proceedings of Machine Learning Research, pages 19315–19342. PMLR.
- Preserving causal constraints in counterfactual explanations for machine learning classifiers. CoRR, abs/1912.03277.
- From softmax to sparsemax: A sparse model of attention and multi-label classification. In Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016, volume 48 of JMLR Workshop and Conference Proceedings, pages 1614–1623. JMLR.org.
- Explaining machine learning classifiers through diverse counterfactual explanations. In FAT* ’20: Conference on Fairness, Accountability, and Transparency, Barcelona, Spain, January 27-30, 2020, pages 607–617. ACM.
- Masked autoregressive flow for density estimation. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pages 2338–2347.
- Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32, pages 8024–8035. Curran Associates, Inc.
- Explaining groups of points in low-dimensional representations. In Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event, volume 119 of Proceedings of Machine Learning Research, pages 7762–7771. PMLR.
- FACE: feasible and actionable counterfactual explanations. In AIES ’20: AAAI/ACM Conference on AI, Ethics, and Society, New York, NY, USA, February 7-8, 2020, pages 344–350. ACM.
- Model agnostic multilevel explanations. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
- Beyond individualized recourse: Interpretable and interactive summaries of actionable recourses. In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., and Lin, H., editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual.
- Variational inference with normalizing flows. In International Conference on Machine Learning, pages 1530–1538. PMLR.
- Russell, C. (2019). Efficient search for diverse coherent explanations. In Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* 2019, Atlanta, GA, USA, January 29-31, 2019, pages 20–28. ACM.
- Towards explainable artificial intelligence. In Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, volume 11700 of Lecture Notes in Computer Science, pages 5–22. Springer.
- Stefanowski, J. (2023). Multi-criteria approaches to explaining black box machine learning models. In Asian Conference on Intelligent Information and Database Systems ACIIDS 2023, pages 195–208. Springer.
- Python reference manual. Centrum voor Wiskunde en Informatica Amsterdam.
- Counterfactual explanations without opening the black box: Automated decisions and the GDPR. CoRR, abs/1711.00399.
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.