RAPNet uses a GNN with level-wise training to learn sparse robust coarse operators that accelerate algebraic multigrid on large PDE and graph problems.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections
RAPNet uses a GNN with level-wise training to learn sparse robust coarse operators that accelerate algebraic multigrid on large PDE and graph problems.