核心概念
Graph generation model GRASP utilizes spectral decomposition and diffusion to efficiently generate graphs while overcoming computational bottlenecks.
統計
"An extensive set of experiments on both synthetic and real world graphs demonstrates the strengths of our model against state-of-the-art alternatives."
"For instance, the Barab´asi-Albert model allows to create graphs that exhibit the scale-free nature found in empirical degree distributions."
引用
"Our permutation invariant model can also handle node features by concatenating them to the eigenvectors of each node."
"Working in the spectral domain is crucial to overcoming the computational bottleneck."