Generating Counterfactual Explanations Using Cardinality Constraints (2404.07502v1)
Abstract: Providing explanations about how machine learning algorithms work and/or make particular predictions is one of the main tools that can be used to improve their trusworthiness, fairness and robustness. Among the most intuitive type of explanations are counterfactuals, which are examples that differ from a given point only in the prediction target and some set of features, presenting which features need to be changed in the original example to flip the prediction for that example. However, such counterfactuals can have many different features than the original example, making their interpretation difficult. In this paper, we propose to explicitly add a cardinality constraint to counterfactual generation limiting how many features can be different from the original example, thus providing more interpretable and easily understantable counterfactuals.
- Towards explanation of dnn-based prediction with guided feature inversion. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’18, pp. 1358–1367, New York, NY, USA, 2018. Association for Computing Machinery. ISBN 9781450355520. doi: 10.1145/3219819.3220099. URL https://doi.org/10.1145/3219819.3220099.
- Techniques for interpretable machine learning. Communications of the ACM, 63(1):68–77, 2019. ISSN 0001-0782. doi: 10.1145/3359786. URL https://doi.org/10.1145/3359786.
- Interpretable explanations of black boxes by meaningful perturbation. In 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3449–3457, 2017. doi: 10.1109/ICCV.2017.371.
- NLIZE: A Perturbation-Driven Visual Interrogation Tool for Analyzing and Interpreting Natural Language Inference Models. IEEE Transactions on Visualization and Computer Graphics, 25(1):651–660, January 2019. ISSN 1941-0506. doi: 10.1109/TVCG.2018.2865230. URL https://ieeexplore.ieee.org/document/8454904. Conference Name: IEEE Transactions on Visualization and Computer Graphics.
- 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, January 2020. Association for Computing Machinery. ISBN 978-1-4503-6936-7. doi: 10.1145/3351095.3372850. URL https://doi.org/10.1145/3351095.3372850.
- Arun Rai. Explainable AI: from black box to glass box. Journal of the Academy of Marketing Science, 48(1):137–141, January 2020. ISSN 1552-7824. doi: 10.1007/s11747-019-00710-5. URL https://doi.org/10.1007/s11747-019-00710-5.
- ”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, KDD ’16, pp. 1135–1144, New York, NY, USA, August 2016. Association for Computing Machinery. ISBN 978-1-4503-4232-2. doi: 10.1145/2939672.2939778. URL https://dl.acm.org/doi/10.1145/2939672.2939778.
- Perturbation-Based Explanations of Prediction Models. In Jianlong Zhou and Fang Chen (eds.), Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent, Human–Computer Interaction Series, pp. 159–175. Springer International Publishing, Cham, 2018. ISBN 978-3-319-90403-0. doi: 10.1007/978-3-319-90403-0˙9. URL https://doi.org/10.1007/978-3-319-90403-0_9.
- CERTIFAI: A Common Framework to Provide Explanations and Analyse the Fairness and Robustness of Black-box Models. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, AIES ’20, pp. 166–172, New York, NY, USA, February 2020. Association for Computing Machinery. ISBN 978-1-4503-7110-0. doi: 10.1145/3375627.3375812. URL https://doi.org/10.1145/3375627.3375812.
- Deep inside convolutional networks: Visualising image classification models and saliency maps. In Yoshua Bengio and Yann LeCun (eds.), 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Workshop Track Proceedings, 2014. URL http://arxiv.org/abs/1312.6034.
- Counterfactual explanations without opening the black box: Automated decisions and the GDPR. CoRR, abs/1711.00399, 2017. URL http://arxiv.org/abs/1711.00399.