Zobrazeno 1 - 10
of 136
pro vyhledávání: '"Wu, Xinliang"'
In representation learning on graph-structured data, many popular graph neural networks (GNNs) fail to capture long-range dependencies, leading to performance degradation. Furthermore, this weakness is magnified when the concerned graph is characteri
Externí odkaz:
http://arxiv.org/abs/2403.03465
Autor:
Chen, Zhuo, Zhang, Wen, Huang, Yufeng, Chen, Mingyang, Geng, Yuxia, Yu, Hongtao, Bi, Zhen, Zhang, Yichi, Yao, Zhen, Song, Wenting, Wu, Xinliang, Yang, Yi, Chen, Mingyi, Lian, Zhaoyang, Li, Yingying, Cheng, Lei, Chen, Huajun
In this work, we share our experience on tele-knowledge pre-training for fault analysis, a crucial task in telecommunication applications that requires a wide range of knowledge normally found in both machine log data and product documents. To organi
Externí odkaz:
http://arxiv.org/abs/2210.11298
Autor:
Zhang, Suilin, Wu, Xinliang, Feng, Xin, Wu, Yan, Zhang, Xiaohan, Wu, Huiling, Zhou, Bingjie, Zhang, Yaqian, Cao, Man, Song, Jingpu, Hou, Zhixia
Publikováno v:
In Scientia Horticulturae 1 October 2024 336
Publikováno v:
In Geoderma September 2024 449
Autor:
Wang, Lina, Gesang, Quzhen, Luo, Jiufu, Wu, Xinliang, Rebi, Ansa, You, Yonggang, Zhou, Jinxing
Publikováno v:
In Global Ecology and Conservation September 2024 53
Publikováno v:
In Geoderma August 2024 448
Publikováno v:
In Catena August 2024 243
Publikováno v:
In Journal of Environmental Management March 2024 354
In representation learning on the graph-structured data, under heterophily (or low homophily), many popular GNNs may fail to capture long-range dependencies, which leads to their performance degradation. To solve the above-mentioned issue, we propose
Externí odkaz:
http://arxiv.org/abs/2105.13795
Heterogeneous graph is a kind of data structure widely existing in real life. Nowadays, the research of graph neural network on heterogeneous graph has become more and more popular. The existing heterogeneous graph neural network algorithms mainly ha
Externí odkaz:
http://arxiv.org/abs/2103.07877