1 code implementation • 21 Feb 2024 • Zheyuan Zhang, Zehong Wang, Shifu Hou, Evan Hall, Landon Bachman, Vincent Galassi, Jasmine White, Nitesh V. Chawla, Chuxu Zhang, Yanfang Ye
The opioid crisis has been one of the most critical society concerns in the United States.
1 code implementation • 14 Feb 2024 • Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye
Graph Neural Networks (GNNs) have demonstrated effectiveness in various graph learning tasks, yet their reliance on message-passing constraints their deployment in latency-sensitive applications such as financial fraud detection.
1 code implementation • 14 Feb 2024 • Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye
To mitigate this, we bring a new insight: for semantically similar graphs, although structural differences lead to significant distribution shift in node embeddings, their impact on subgraph embeddings could be marginal.
no code implementations • 3 Oct 2022 • Zehong Wang, Qi Li, Donghua Yu
We argue that when learning high-order information from temporal graphs, we encounter two challenges, i. e., computational inefficiency and over-smoothing, that cannot be solved by conventional techniques applied on static graphs.
1 code implementation • 1 Oct 2022 • Zehong Wang, Qi Li, Donghua Yu, Xiaolong Han, Xiao-Zhi Gao, Shigen Shen
How to mitigate the sampling bias for heterogeneous GCL is another important problem.