Zobrazeno 1 - 10
of 490
pro vyhledávání: '"Huang, Zhehao"'
Autor:
Huang, Zhehao, Cheng, Xinwen, Zheng, JingHao, Wang, Haoran, He, Zhengbao, Li, Tao, Huang, Xiaolin
Machine unlearning (MU) has emerged to enhance the privacy and trustworthiness of deep neural networks. Approximate MU is a practical method for large-scale models. Our investigation into approximate MU starts with identifying the steepest descent di
Externí odkaz:
http://arxiv.org/abs/2409.19732
Autor:
Ehrling, Sebastian, Senkovska, Irena, Efimova, Anastasia, Bon, Volodymyr, Abylgazina, Leila, Petkov, Petko, Evans, Jack D., Attallah, Ahmed Gamal, Wharmby, Michael Thomas, Roslova, Maria, Huang, Zhehao, Tanaka, Hideki, Wagner, Andreas, Schmidt, Peer, Kaskel, Stefan
DUT-8(Ni) metal–organic framework (MOF) belongs to the family of flexible pillared layer materials. The desolvated framework can be obtained in the open pore form (op) or in the closed pore form (cp), depending on the crystal size regime. In the pr
Externí odkaz:
https://tud.qucosa.de/id/qucosa%3A89988
https://tud.qucosa.de/api/qucosa%3A89988/attachment/ATT-0/
https://tud.qucosa.de/api/qucosa%3A89988/attachment/ATT-0/
Autor:
Sporrer, Lukas, Zhou, Guojun, Wang, Mingchao, Balos, Vasileios, Revuelta, Sergio, Jastrzembski, Kamil, Loeffler, Markus, Petkov, Petko, Heine, Thomas, Kuc, Angieszka, Canovas, Enrique, Huang, Zhehao, Feng, Xinliang, Dong, Renhao
Publikováno v:
Angew. Chem. Int. Ed. 2023, 62, e202300186
Two-dimensional conjugated metal-organic frameworks (2D c-MOFs) are emerging as a unique class of 2D electronic materials. However, intrinsically semiconducting 2D c-MOFs with gaps in the Vis-NIR and high charge carrier mobility have been rare. Most
Externí odkaz:
http://arxiv.org/abs/2405.17899
Machine unlearning (MU) aims to eliminate information that has been learned from specific training data, namely forgetting data, from a pre-trained model. Currently, the mainstream of existing MU methods involves modifying the forgetting data with in
Externí odkaz:
http://arxiv.org/abs/2405.15495
Machine Unlearning (MU) is to forget data from a well-trained model, which is practically important due to the "right to be forgotten". In this paper, we start from the fundamental distinction between training data and unseen data on their contributi
Externí odkaz:
http://arxiv.org/abs/2402.15109
Online continual learning is a challenging problem where models must learn from a non-stationary data stream while avoiding catastrophic forgetting. Inter-class imbalance during training has been identified as a major cause of forgetting, leading to
Externí odkaz:
http://arxiv.org/abs/2311.06460
Autor:
Huang, Zhehao1,2 (AUTHOR) zhehao.huang@mmk.su.se, Geilhufe, Richard Matthias3 (AUTHOR)
Publikováno v:
Small Science. Oct2024, Vol. 4 Issue 10, p1-15. 15p.
Autor:
Li, Tao, Huang, Zhehao, Wu, Yingwen, He, Zhengbao, Tao, Qinghua, Huang, Xiaolin, Lin, Chih-Jen
Training deep neural networks (DNNs) in low-dimensional subspaces is a promising direction for achieving efficient training and better generalization performance. Our previous work extracts the subspaces by performing the dimension reduction method o
Externí odkaz:
http://arxiv.org/abs/2205.13104
The score-based query attacks (SQAs) pose practical threats to deep neural networks by crafting adversarial perturbations within dozens of queries, only using the model's output scores. Nonetheless, we note that if the loss trend of the outputs is sl
Externí odkaz:
http://arxiv.org/abs/2205.12134
Publikováno v:
In Energy 1 December 2024 311