Mlpinit: Embarrassingly simple gnn training acceleration with mlp initialization

X Han, T Zhao, Y Liu, X Hu, N Shah - arXiv preprint arXiv:2210.00102, 2022 - arxiv.org
Training graph neural networks (GNNs) on large graphs is complex and extremely time
consuming. This is attributed to overheads caused by sparse matrix multiplication, which are …

MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization

X Han, T Zhao, Y Liu, X Hu, N Shah - The Eleventh International … - openreview.net
Training graph neural networks (GNNs) on large graphs is complex and extremely time
consuming. This is attributed to overheads caused by sparse matrix multiplication, which are …

MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization

X Han, T Zhao, Y Liu, X Hu, N Shah - arXiv e-prints, 2022 - ui.adsabs.harvard.edu
Training graph neural networks (GNNs) on large graphs is complex and extremely time
consuming. This is attributed to overheads caused by sparse matrix multiplication, which are …