Problems with Shapley-value-based explanations as feature importance measures IE Kumar, S Venkatasubramanian, C Scheidegger, S Friedler International Conference on Machine Learning, 5491-5500, 2020 | 393 | 2020 |
The fallacy of AI functionality ID Raji, IE Kumar, A Horowitz, A Selbst 2022 ACM Conference on Fairness, Accountability, and Transparency, 959-972, 2022 | 159 | 2022 |
Shapley Residuals: Quantifying the limits of the Shapley value for explanations IE Kumar, C Scheidegger, S Venkatasubramanian, S Friedler Advances in Neural Information Processing Systems 34, 26598-26608, 2021 | 51 | 2021 |
Epistemic values in feature importance methods: Lessons from feminist epistemology L Hancox-Li, IE Kumar Proceedings of the 2021 ACM Conference on Fairness, Accountability, and …, 2021 | 37 | 2021 |
Equalizing credit opportunity in algorithms: Aligning algorithmic fairness research with US fair lending regulation IE Kumar, KE Hines, JP Dickerson Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, 357-368, 2022 | 19 | 2022 |
Deconstructing design decisions: Why courts must interrogate machine learning and other technologies AD Selbst, S Venkatasubramanian, IE Kumar Ohio State Law Journal, 23-22, 2024 | 7* | 2024 |
To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models C Cousins, IE Kumar, S Venkatasubramanian arXiv preprint arXiv:2402.18803, 2024 | 1 | 2024 |
Systems and methods for risk factor predictive modeling with model explanations M Maier, S Li, H Carlotto, I Kumar US Patent 11,710,564, 2023 | | 2023 |