Zobrazeno 1 - 10
of 63
pro vyhledávání: '"Yang, Jielong"'
The performance of graph neural networks (GNNs) is susceptible to discrepancies between training and testing sample distributions. Prior studies have attempted to enhance GNN performance by reconstructing node features during the testing phase withou
Externí odkaz:
http://arxiv.org/abs/2410.09708
Due to inappropriate sample selection and limited training data, a distribution shift often exists between the training and test sets. This shift can adversely affect the test performance of Graph Neural Networks (GNNs). Existing approaches mitigate
Externí odkaz:
http://arxiv.org/abs/2308.09259
In node classification using graph neural networks (GNNs), a typical model generates logits for different class labels at each node. A softmax layer often outputs a label prediction based on the largest logit. We demonstrate that it is possible to in
Externí odkaz:
http://arxiv.org/abs/2305.00139
In graph neural networks (GNNs), both node features and labels are examples of graph signals, a key notion in graph signal processing (GSP). While it is common in GSP to impose signal smoothness constraints in learning and estimation tasks, it is unc
Externí odkaz:
http://arxiv.org/abs/2304.03507
Autor:
Qu, Bohao, Cao, Xiaofeng, Yang, Jielong, Chen, Hechang, Yi, Chang, Tsang, Ivor W., Ong, Yew-Soon
Markov Decision Process (MDP) presents a mathematical framework to formulate the learning processes of agents in reinforcement learning. MDP is limited by the Markovian assumption that a reward only depends on the immediate state and action. However,
Externí odkaz:
http://arxiv.org/abs/2302.14509
Graph neural networks (GNNs) have achieved great success in many scenarios with graph-structured data. However, in many real applications, there are three issues when applying GNNs: graphs are unknown, nodes have noisy features, and graphs contain no
Externí odkaz:
http://arxiv.org/abs/2210.03907
Autor:
He, Jin, Chen, Si, Yang, Fan, Huang, Weifeng, Ni, Guangming, Yang, Jielong, Huang, Yongsheng, Ge, Xin, Liu, Linbo
Publikováno v:
In Optics and Laser Technology December 2024 179
Publikováno v:
In Knowledge-Based Systems 5 September 2024 299
Publikováno v:
In Expert Systems With Applications 15 April 2024 240
Autor:
Ge, Xin, He, Jin, Chen, Si, Ni, Guangming, Xiong, Qiaozhou, Yang, Jielong, Yu, Lequan, Liu, Linbo, Bo, En
Publikováno v:
In Optics and Lasers in Engineering March 2024 174