| A benchmark for interpretability methods in deep neural networks S Hooker, D Erhan, PJ Kindermans, B Kim Advances in neural information processing systems 32, 2019 | 646* | 2019 |
| The state of sparsity in deep neural networks T Gale, E Elsen, S Hooker arXiv preprint arXiv:1902.09574, 2019 | 645 | 2019 |
| The (un) reliability of saliency methods PJ Kindermans, S Hooker, J Adebayo, M Alber, KT Schütt, S Dähne, ... Explainable AI: Interpreting, explaining and visualizing deep learning, 267-280, 2019 | 639 | 2019 |
| 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 |
| The hardware lottery S Hooker Communications of the ACM 64 (12), 58-65, 2021 | 160 | 2021 |
| What do compressed deep neural networks forget? S Hooker, A Courville, G Clark, Y Dauphin, A Frome WHI ICML 2019, 2019 | 159* | 2019 |
| Moving beyond “algorithmic bias is a data problem” S Hooker Patterns 2 (4), 2021 | 143 | 2021 |
| Characterising bias in compressed models S Hooker, N Moorosi, G Clark, S Bengio, E Denton arXiv preprint arXiv:2010.03058, 2020 | 139 | 2020 |
| Estimating example difficulty using variance of gradients C Agarwal, D D'souza, S Hooker IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022, 2020 | 60 | 2020 |
| Randomness in neural network training: Characterizing the impact of tooling D Zhuang, X Zhang, S Song, S Hooker Proceedings of Machine Learning and Systems 4, 316-336, 2022 | 49 | 2022 |
| The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation O Ahia, J Kreutzer, S Hooker Findings of EMNLP 2021, 2021 | 32 | 2021 |
| Efficient methods for natural language processing: A survey M Treviso, JU Lee, T Ji, B Aken, Q Cao, MR Ciosici, M Hassid, K Heafield, ... Transactions of the Association for Computational Linguistics 11, 826-860, 2023 | 31 | 2023 |
| Keep the gradients flowing: Using gradient flow to study sparse network optimization K Tessera, S Hooker, B Rosman arXiv preprint arXiv:2102.01670, 2021 | 18 | 2021 |
| Frontier AI regulation: Managing emerging risks to public safety M Anderljung, J Barnhart, J Leung, A Korinek, C O'Keefe, J Whittlestone, ... arXiv preprint arXiv:2307.03718, 2023 | 16 | 2023 |
| A tale of two long tails D D'souza, Z Nussbaum, C Agarwal, S Hooker arXiv preprint arXiv:2107.13098, 2021 | 15 | 2021 |
| Large language models are not zero-shot communicators L Ruis, A Khan, S Biderman, S Hooker, T Rocktäschel, E Grefenstette arXiv preprint arXiv:2210.14986, 2022 | 14 | 2022 |
| Evaluating the Social Impact of Generative AI Systems in Systems and Society I Solaiman, Z Talat, W Agnew, L Ahmad, D Baker, SL Blodgett, ... arXiv preprint arXiv:2306.05949, 2023 | 13 | 2023 |
| Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics SA Siddiqui, N Rajkumar, T Maharaj, D Krueger, S Hooker International Conference on Learning Representations, 2023, 2022 | 13 | 2022 |
| Toward trustworthy AI development: mechanisms for supporting verifiable claims (2020) M Brundage, S Avin, J Wang, H Belfield, G Krueger, G Hadfield, H Khlaaf, ... arXiv preprint arXiv:2004.07213, 2020 | 11 | 2020 |
| On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research L Pozzobon, B Ermis, P Lewis, S Hooker arXiv preprint arXiv:2304.12397, 2023 | 7 | 2023 |
Pieter-Jan KindermansStaff Research Scientist, Google DeepmindVerified email at google.com
