PiPAD: Pipelined and Parallel Dynamic GNN Training on GPUs

no code implementations • 1 Jan 2023 • Chunyang Wang, Desen Sun, Yuebin Bai

Dynamic Graph Neural Networks (DGNNs) have been broadly applied in various real-life applications, such as link prediction and pandemic forecast, to capture both static structural information and temporal characteristics from dynamic graphs.

Link Prediction