no code implementations • 23 Apr 2024 • Qincheng Lu, Sitao Luan, Xiao-Wen Chang
To our knowledge, we are the first to shed light on the connection between the system model and graph convolution, and the first to design the data-dependent attention scores for graph convolution.
no code implementations • 3 Mar 2024 • Qincheng Lu, Jiaqi Zhu, Sitao Luan, Xiao-Wen Chang
However, since it only incorporates information from immediate neighborhood, it lacks the ability to capture long-range and global graph information, leading to unsatisfactory performance on some datasets, particularly on heterophilic graphs.
no code implementations • 14 Feb 2024 • Ziyang Song, Qincheng Lu, He Zhu, Yue Li
Learning time-series representations for discriminative tasks has been a long-standing challenge.
no code implementations • 29 Nov 2023 • Ziyang Song, Qincheng Lu, Hao Xu, David L. Buckeridge, Yue Li
This underscores the limitations of the existing transformer-based architectures, particularly their scalability to handle large-scale data and ability to capture long-term temporal dependencies.
1 code implementation • 25 Apr 2023 • Sitao Luan, Chenqing Hua, Minkai Xu, Qincheng Lu, Jiaqi Zhu, Xiao-Wen Chang, Jie Fu, Jure Leskovec, Doina Precup
Homophily principle, i. e., nodes with the same labels are more likely to be connected, has been believed to be the main reason for the performance superiority of Graph Neural Networks (GNNs) over Neural Networks on node classification tasks.
no code implementations • 30 Oct 2022 • Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Xiao-Wen Chang, Doina Precup
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by additionally making use of graph structure based on the relational inductive bias (edge bias), rather than treating the nodes as collections of independent and identically distributed (i. i. d.)
1 code implementation • 14 Oct 2022 • Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Mingde Zhao, Shuyuan Zhang, Xiao-Wen Chang, Doina Precup
ACM is more powerful than the commonly used uni-channel framework for node classification tasks on heterophilic graphs and is easy to be implemented in baseline GNN layers.
Inductive Bias Node Classification on Non-Homophilic (Heterophilic) Graphs
no code implementations • 29 Sep 2021 • Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Mingde Zhao, Shuyuan Zhang, Xiao-Wen Chang, Doina Precup
In this paper, we first show that not all cases of heterophily are harmful for GNNs with aggregation operation.
no code implementations • 12 Sep 2021 • Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Mingde Zhao, Shuyuan Zhang, Xiao-Wen Chang, Doina Precup
In this paper, we first show that not all cases of heterophily are harmful for GNNs with aggregation operation.
Ranked #1 on Node Classification on Pubmed
no code implementations • NeurIPS 2021 • Sitao Luan, Chenqing Hua, Qincheng Lu, Jiaqi Zhu, Mingde Zhao, Shuyuan Zhang, Xiao-Wen Chang, Doina Precup
In this paper, we first show that not all cases of heterophily are harmful for GNNs with aggregation operation.