Zobrazeno 1 - 10
of 288
pro vyhledávání: '"Shen, Yuesong"'
Autor:
Shen, Yuesong, Daheim, Nico, Cong, Bai, Nickl, Peter, Marconi, Gian Maria, Bazan, Clement, Yokota, Rio, Gurevych, Iryna, Cremers, Daniel, Khan, Mohammad Emtiyaz, Möllenhoff, Thomas
We give extensive empirical evidence against the common belief that variational learning is ineffective for large neural networks. We show that an optimizer called Improved Variational Online Newton (IVON) consistently matches or outperforms Adam for
Externí odkaz:
http://arxiv.org/abs/2402.17641
It is by now a well known fact in the graph learning community that the presence of bottlenecks severely limits the ability of graph neural networks to propagate information over long distances. What so far has not been appreciated is that, counter-i
Externí odkaz:
http://arxiv.org/abs/2310.00431
Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on in-domain
Externí odkaz:
http://arxiv.org/abs/2302.05118
Current graph neural networks (GNNs) that tackle node classification on graphs tend to only focus on nodewise scores and are solely evaluated by nodewise metrics. This limits uncertainty estimation on graphs since nodewise marginals do not fully char
Externí odkaz:
http://arxiv.org/abs/2210.15575
Autor:
Shen, Yuesong, Cremers, Daniel
Neural networks are known to produce poor uncertainty estimations, and a variety of approaches have been proposed to remedy this issue. This includes deep ensemble, a simple and effective method that achieves state-of-the-art results for uncertainty-
Externí odkaz:
http://arxiv.org/abs/2210.06436
Given the importance of getting calibrated predictions and reliable uncertainty estimations, various post-hoc calibration methods have been developed for neural networks on standard multi-class classification tasks. However, these methods are not wel
Externí odkaz:
http://arxiv.org/abs/2210.06391
Node features and structural information of a graph are both crucial for semi-supervised node classification problems. A variety of graph neural network (GNN) based approaches have been proposed to tackle these problems, which typically determine out
Externí odkaz:
http://arxiv.org/abs/2107.13059
Publikováno v:
In Applied Catalysis B: Environment and Energy January 2025 360
Autor:
Shen, Yuesong, Cremers, Daniel
The last decade has witnessed a boom of deep learning research and applications achieving state-of-the-art results in various domains. However, most advances have been established empirically, and their theoretical analysis remains lacking. One major
Externí odkaz:
http://arxiv.org/abs/2006.16856
Autor:
Sun, Bin, Liu, Youlin, Hu, Yongji, Zhou, Hong, Zhang, Zhongyuan, Wang, Jianhai, Gu, Sasa, Shen, Yuesong
Publikováno v:
In Applied Surface Science 15 December 2023 640