Scalable Subgraph Sampling via Resistance Curvature
Quick summary
arXiv:2609.27209v1 Announce Type: cross Abstract: Subgraph sampling reduces the training cost of large-scale graph neural networks, but sampling criteria may overlook the geometric roles of edges. We propose a resistance-curvature-guided sampling framework built on ERC-LG, a curvature approximation method for large-scale graphs. ERC-LG combines Johnson-Lindenstrauss projections with regularized multi-GPU batched conjugate gradient solvers, avoiding explicit Laplacian pseudoinverse computation and full embedding storage. The resulting curvature informs node- and edge-sampling probabilities for
Key takeaways
- arXiv:2609.27209v1 Announce Type: cross Abstract: Subgraph sampling reduces the training cost of large-scale graph neural networks, but sampling criteria may overlook the geometric roles of edges.
- We propose a resistance-curvature-guided sampling framework built on ERC-LG, a curvature approximation method for large-scale graphs.
- ERC-LG combines Johnson-Lindenstrauss projections with regularized multi-GPU batched conjugate gradient solvers, avoiding explicit Laplacian pseudoinverse computation and full embedding storage.
Why it matters
“Scalable Subgraph Sampling via Resistance Curvature” exposes the compute, energy and supply-chain layer behind model competition. Capacity shifts can influence model costs, service availability and the ability of smaller companies to compete.
Member comments