no code implementations • 6 Oct 2021 • Taige Zhao, XiangYu Song, JianXin Li, Wei Luo, Imran Razzak
We first propose a graph augmentation-based partition (GAD-Partition) that can divide original graph into augmented subgraphs to reduce communication by selecting and storing as few significant nodes of other processors as possible while guaranteeing the accuracy of the training.