EDiS: Edge Disjoint Subgraph Sparsification Framework for Graph Neural Networks
EDiS sparsifies GNN training by caching edge-disjoint subgraphs and recomposing them each epoch under an edge budget.
1 stories, newest first · one card per story
EDiS sparsifies GNN training by caching edge-disjoint subgraphs and recomposing them each epoch under an edge budget.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views