| Understanding global feature contributions with additive importance measures I Covert, S Lundberg, SI Lee arXiv preprint arXiv:2004.00668, 2020 | 423 | 2020 |
| Neural granger causality for nonlinear time series A Tank, I Covert, N Foti, A Shojaie, E Fox arXiv preprint arXiv:1802.05842, 2018 | 383* | 2018 |
| Explaining by removing: a unified framework for model explanation I Covert, S Lundberg, SI Lee arXiv preprint arXiv:2011.14878, 2020 | 295 | 2020 |
| What does a platypus look like? Generating customized prompts for zero-shot image classification S Pratt, I Covert, R Liu, A Farhadi Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023 | 239 | 2023 |
| Algorithms to estimate Shapley value feature attributions H Chen, IC Covert, SM Lundberg, SI Lee Nature Machine Intelligence 5 (6), 590-601, 2023 | 214 | 2023 |
| Improving KernelSHAP: Practical Shapley value estimation using linear regression I Covert, SI Lee International Conference on Artificial Intelligence and Statistics, 3457-3465, 2021 | 209* | 2021 |
| FastSHAP: Real-time Shapley value estimation N Jethani, M Sudarshan, I Covert, SI Lee, R Ranganath arXiv e-prints, arXiv: 2107.07436, 2021 | 150 | 2021 |
| Temporal graph convolutional networks for automatic seizure detection IC Covert, B Krishnan, I Najm, J Zhan, M Shore, J Hixson, MJ Po Machine learning for healthcare conference, 160-180, 2019 | 97 | 2019 |
| Feature removal is a unifying principle for model explanation methods I Covert, S Lundberg, SI Lee arXiv preprint arXiv:2011.03623, 2020 | 41 | 2020 |
| Learning to maximize mutual information for dynamic feature selection I Covert, W Qiu, M Lu, N Kim, N White, SI Lee arXiv preprint arXiv:2301.00557, 2023 | 33 | 2023 |
| An interpretable and sparse neural network model for nonlinear granger causality discovery A Tank, I Covert, NJ Foti, A Shojaie, EB Fox arXiv preprint arXiv:1711.08160, 2017 | 31 | 2017 |
| Learning to estimate Shapley values with vision transformers I Covert, C Kim, SI Lee arXiv preprint arXiv:2206.05282, 2022 | 30 | 2022 |
| Predictive and robust gene selection for spatial transcriptomics I Covert, R Gala, T Wang, K Svoboda, U Sümbül, SI Lee Nature Communications 14 (1), 2091, 2023 | 20 | 2023 |
| On the robustness of removal-based feature attributions C Lin, I Covert, SI Lee arXiv preprint arXiv:2306.07462, 2023 | 10 | 2023 |
| Disrupting model training with adversarial shortcuts I Evtimov, I Covert, A Kusupati, T Kohno arXiv preprint arXiv:2106.06654, 2021 | 9 | 2021 |
| Dragonfly: multi-resolution zoom-in encoding enhances vision-language models R Thapa, K Chen, I Covert, R Chalamala, B Athiwaratkun, SL Song, J Zou arXiv preprint arXiv:2406.00977, 2024 | 8* | 2024 |
| Deep unsupervised feature selection I Covert, U Sumbul, SI Lee | 3 | 2019 |
| Scaling laws for the value of individual data points in machine learning I Covert, W Ji, T Hashimoto, J Zou arXiv preprint arXiv:2405.20456, 2024 | 2 | 2024 |
| Feature selection in the contrastive analysis setting E Weinberger, I Covert, SI Lee Advances in Neural Information Processing Systems 36, 2024 | 2 | 2024 |
| Stochastic amortization: a unified approach to accelerate feature and data attribution I Covert, C Kim, SI Lee, J Zou, T Hashimoto arXiv preprint arXiv:2401.15866, 2024 | 2 | 2024 |
Su-In LeeComputer Science & Engineering, University of WashingtonVerified email at cs.washington.edu