Mlpinit: Embarrassingly simple gnn training acceleration with mlp initialization
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 …
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 …
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 …
consuming. This is attributed to overheads caused by sparse matrix multiplication, which are …