A Dependency-Aware Multi-GPU Training Framework for Temporal Graph Neural Networks
Temporal graph neural networks (TGNNs) achieve superior performance in many dynamic graph learning tasks. These models use node state vectors (i.e., memories) to capture and record graph changes (i.e., events), and then exploit these memories to assist prediction. However, this memory-centric design makes multi-GPU tra...
Yang Zhao, Yue-Zhen Dai, Liang Qiao et al.
· 0 citations