首页 > AI前沿 > Scalable Subgraph Sampling via Resistance Curvature

Scalable Subgraph Sampling via Resistance Curvature

arXiv机器学习 2026-09-23 09:16 6 阅读 查看原文

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 constructing GNN training subgraphs.

Experiments show numerical agreement with pseudoinverse-based curvature and reduced runtime compared with CG-only computation.

ERC-LG-based sampling variants achieve the highest mean accuracy on six of seven real-world datasets in downstream node classification.