Zobrazeno 1 - 10
of 35 286
pro vyhledávání: '"An, LiHui"'
Autor:
Zheng, Yilun, Zhang, Zhuofan, Wang, Ziming, Li, Xiang, Luan, Sitao, Peng, Xiaojiang, Chen, Lihui
To improve the performance of Graph Neural Networks (GNNs), Graph Structure Learning (GSL) has been extensively applied to reconstruct or refine original graph structures, effectively addressing issues like heterophily, over-squashing, and noisy stru
Externí odkaz:
http://arxiv.org/abs/2411.07672
Graph Neural Networks (GNNs) have demonstrated strong capabilities in processing structured data. While traditional GNNs typically treat each feature dimension equally during graph convolution, we raise an important question: Is the graph convolution
Externí odkaz:
http://arxiv.org/abs/2411.07663
Autor:
Wang, Wenxiao, Gu, Lihui, Zhang, Liye, Luo, Yunxiang, Dai, Yi, Shen, Chen, Xie, Liang, Lin, Binbin, He, Xiaofei, Ye, Jieping
The exponential growth of knowledge and the increasing complexity of interdisciplinary research pose significant challenges for researchers, including information overload and difficulties in exploring novel ideas. The advancements in large language
Externí odkaz:
http://arxiv.org/abs/2410.23166
GESH-Net: Graph-Enhanced Spherical Harmonic Convolutional Networks for Cortical Surface Registration
Currently, cortical surface registration techniques based on classical methods have been well developed. However, a key issue with classical methods is that for each pair of images to be registered, it is necessary to search for the optimal transform
Externí odkaz:
http://arxiv.org/abs/2410.14805
EigenSR: Eigenimage-Bridged Pre-Trained RGB Learners for Single Hyperspectral Image Super-Resolution
Single hyperspectral image super-resolution (single-HSI-SR) aims to improve the resolution of a single input low-resolution HSI. Due to the bottleneck of data scarcity, the development of single-HSI-SR lags far behind that of RGB natural images. In r
Externí odkaz:
http://arxiv.org/abs/2409.04050
Full waveform inversion (FWI) plays a crucial role in the field of geophysics. There has been lots of research about applying deep learning (DL) methods to FWI. The success of DL-FWI relies significantly on the quantity and diversity of the datasets.
Externí odkaz:
http://arxiv.org/abs/2408.08005
The construction of Ekman boundary layer solutions near the non-flat boundaries presents a complex challenge, with limited research on this issue. In Masmoudi's pioneering work [Comm. Pure Appl. Math. 53 (2000), 432--483], the Ekman boundary layer so
Externí odkaz:
http://arxiv.org/abs/2408.07582
Autor:
Que, Xinglu, He, Qingyu, Zhou, Lihui, Lei, Shiming, Schoop, Leslie, Huang, Dennis, Takagi, Hidenori
The collective reorganization of electrons into a charge density wave (CDW) inside a crystal has long served as a textbook example of an ordered phase in condensed matter physics. Two-dimensional square lattices with $p$ electrons are well-suited to
Externí odkaz:
http://arxiv.org/abs/2408.07351
The contextual bandit has been identified as a powerful framework to formulate the recommendation process as a sequential decision-making process, where each item is regarded as an arm and the objective is to minimize the regret of $T$ rounds. In thi
Externí odkaz:
http://arxiv.org/abs/2408.05586
Autor:
Tan, Frank Lihui, Do, Youngah
This study investigates how learners organize perceptual space in early phonetic acquisition by advancing previous studies in two key aspects. Firstly, it examines the shape of the learned hidden representation as well as its ability to categorize ph
Externí odkaz:
http://arxiv.org/abs/2407.18501