1 code implementation • 7 Dec 2022 • Shuai Zheng, Zhenfeng Zhu, Zhizhe Liu, Youru Li, Yao Zhao
Graph neural networks (GNNs) have shown remarkable performance on homophilic graph data while being far less impressive when handling non-homophilic graph data due to the inherent low-pass filtering property of GNNs.
1 code implementation • 15 Nov 2022 • Youru Li, Zhenfeng Zhu, Xiaobo Guo, Shaoshuai Li, Yuchen Yang, Yao Zhao
Moreover, the hierarchical representations at both instance level and channel level can be coordinated by the heterogeneous information aggregation under the guidance of global view.
no code implementations • 9 Nov 2018 • Youru Li, Zhenfeng Zhu, Deqiang Kong, Hua Han, Yao Zhao
To address this issue, an evolutionary attention-based LSTM training with competitive random search is proposed for multivariate time series prediction.