Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Deng, Chenhui"'
While graph neural networks (GNNs) have gained popularity for learning circuit representations in various electronic design automation (EDA) tasks, they face challenges in scalability when applied to large graphs and exhibit limited generalizability
Externí odkaz:
http://arxiv.org/abs/2403.01317
Graph transformers (GTs) have emerged as a promising architecture that is theoretically more expressive than message-passing graph neural networks (GNNs). However, typical GT models have at least quadratic complexity and thus cannot scale to large gr
Externí odkaz:
http://arxiv.org/abs/2403.01232
Modern graph neural networks (GNNs) can be sensitive to changes in the input graph structure and node features, potentially resulting in unpredictable behavior and degraded performance. In this work, we introduce a spectral framework known as SAGMAN
Externí odkaz:
http://arxiv.org/abs/2402.08653
Publikováno v:
Learning on Graphs Conference (LoG), 2022
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data. However, recent studies show that GNNs are vulnerable to graph adversarial attacks. Although there are several defense m
Externí odkaz:
http://arxiv.org/abs/2201.12741
A black-box spectral method is introduced for evaluating the adversarial robustness of a given machine learning (ML) model. Our approach, named SPADE, exploits bijective distance mapping between the input/output graphs constructed for approximating t
Externí odkaz:
http://arxiv.org/abs/2102.03716
Publikováno v:
International Conference on Learning Representations, ICLR 2020
Graph embedding techniques have been increasingly deployed in a multitude of different applications that involve learning on non-Euclidean data. However, existing graph embedding models either fail to incorporate node attribute information during tra
Externí odkaz:
http://arxiv.org/abs/1910.02370
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Journal of Crystal Growth 1 September 2022 593
Publikováno v:
In Journal of the European Ceramic Society June 2022 42(6):2726-2734
Autor:
Deng, Chenhui1,2 (AUTHOR) chenhuisnow@126.com, Bai, Hongying3 (AUTHOR), Zhao, Ting3 (AUTHOR), Ma, Xinping1 (AUTHOR), Li, Wenzheng1 (AUTHOR), Xie, Meilin1 (AUTHOR)
Publikováno v:
Theoretical & Applied Climatology. Apr2022, Vol. 148 Issue 1/2, p131-143. 13p. 3 Charts, 1 Graph, 5 Maps.