Towards a unified game-theoretic view of adversarial perturbations and robustness J Ren, D Zhang, Y Wang, L Chen, Z Zhou, Y Chen, X Cheng, X Wang, ... Advances in Neural Information Processing Systems 34, 3797-3810, 2021 | 40* | 2021 |
Can we faithfully represent masked states to compute shapley values on a dnn? J Ren, Z Zhou, Q Chen, Q Zhang arXiv preprint arXiv:2105.10719, 2021 | 21* | 2021 |
Defects of convolutional decoder networks in frequency representation L Tang, W Shen, Z Zhou, Y Chen, Q Zhang arXiv preprint arXiv:2210.09020, 2022 | 9 | 2022 |
Going beyond linear mode connectivity: The layerwise linear feature connectivity Z Zhou, Y Yang, X Yang, J Yan, W Hu Advances in Neural Information Processing Systems 36, 2024 | 7 | 2024 |
Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory Y Chen, Z Zhou, J Yan arXiv preprint arXiv:2310.06756, 2023 | 1 | 2023 |
Batch Normalization Is Blind to the First and Second Derivatives of the Loss Z Zhou, W Shen, H Chen, L Tang, Y Chen, Q Zhang Proceedings of the AAAI Conference on Artificial Intelligence 38 (18), 20010 …, 2024 | | 2024 |
Cross-Task Linearity Emerges in the Pretraining-Finetuning Paradigm Z Zhou, Z Chen, Y Chen, B Zhang, J Yan arXiv preprint arXiv:2402.03660, 2024 | | 2024 |