| Understanding black-box predictions via influence functions PW Koh, P Liang International conference on machine learning, 1885-1894, 2017 | 2563 | 2017 |
| On the opportunities and risks of foundation models R Bommasani, DA Hudson, E Adeli, R Altman, S Arora, S von Arx, ... arXiv preprint arXiv:2108.07258, 2021 | 1959 | 2021 |
| Mobility network models of COVID-19 explain inequities and inform reopening S Chang*, E Pierson*, PW Koh*, J Gerardin, B Redbird, D Grusky, ... Nature, 1-6, 2020 | 1339 | 2020 |
| Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization S Sagawa*, PW Koh*, TB Hashimoto, P Liang International Conference on Learning Representations, 2019 | 1138 | 2019 |
| WILDS: A Benchmark of in-the-Wild Distribution Shifts PW Koh*, S Sagawa*, H Marklund, SM Xie, M Zhang, A Balsubramani, ... International Conference on Machine Learning, 5637-5664, 2021 | 939 | 2021 |
| Certified defenses for data poisoning attacks J Steinhardt*, PW Koh*, PS Liang Advances in neural information processing systems, 3517-3529, 2017 | 737 | 2017 |
| Peer and self assessment in massive online classes C Kulkarni, PW Koh, H Le, D Chia, K Papadopoulos, J Cheng, D Koller, ... Design Thinking Research, 131-168, 2015 | 562 | 2015 |
| On random weights and unsupervised feature learning A Saxe, PW Koh, Z Chen, M Bhand, B Suresh, AY Ng Proceedings of the 28th International Conference on Machine Learning (ICML …, 2011 | 518 | 2011 |
| Concept Bottleneck Models PW Koh*, T Nguyen*, YS Tang*, S Mussmann, E Pierson, B Kim, P Liang International Conference on Machine Learning, 5338-5348, 2020 | 449 | 2020 |
| Tiled convolutional neural networks QV Le, J Ngiam, Z Chen, D Chia, PW Koh, AY Ng Advances in Neural Information Processing Systems, 1279-1287, 2010 | 449* | 2010 |
| Mapping the pairwise choices leading from pluripotency to human bone, heart, and other mesoderm cell types KM Loh*, A Chen*, PW Koh, TZ Deng, R Sinha, JM Tsai, AA Barkal, ... Cell 166 (2), 451-467, 2016 | 397 | 2016 |
| Sparse filtering J Ngiam, PW Koh, Z Chen, SA Bhaskar, AY Ng Advances in Neural Information Processing Systems, 1125-1133, 2011 | 345 | 2011 |
| Just train twice: Improving group robustness without training group information EZ Liu, B Haghgoo, AS Chen, A Raghunathan, PW Koh, S Sagawa, ... International Conference on Machine Learning, 6781-6792, 2021 | 312 | 2021 |
| Toward trustworthy AI development: mechanisms for supporting verifiable claims M Brundage, S Avin, J Wang, H Belfield, G Krueger, G Hadfield, H Khlaaf, ... arXiv preprint arXiv:2004.07213, 2020 | 286 | 2020 |
| An investigation of why overparameterization exacerbates spurious correlations S Sagawa*, A Raghunathan*, PW Koh*, P Liang International Conference on Machine Learning, 8346-8356, 2020 | 278 | 2020 |
| Stronger data poisoning attacks break data sanitization defenses PW Koh, J Steinhardt, P Liang Machine Learning, 1-47, 2022 | 210 | 2022 |
| Learning deep energy models J Ngiam, Z Chen, PW Koh, AY Ng ICML, 2011 | 208 | 2011 |
| Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization JP Miller, R Taori, A Raghunathan, S Sagawa, PW Koh, V Shankar, ... International Conference on Machine Learning, 7721-7735, 2021 | 182 | 2021 |
| On the accuracy of influence functions for measuring group effects PW Koh*, KS Ang*, H Teo*, PS Liang Advances in Neural Information Processing Systems, 5254-5264, 2019 | 157 | 2019 |
| Extending the WILDS benchmark for unsupervised adaptation S Sagawa*, PW Koh*, T Lee*, I Gao*, SM Xie, K Shen, A Kumar, W Hu, ... arXiv preprint arXiv:2112.05090, 2021 | 74 | 2021 |
Percy LiangAssociate Professor of Computer Science, Stanford UniversityVerified email at cs.stanford.edu
