no code implementations • 21 Jul 2021 • Dominik Kloepfer, Angelica I. Aviles-Rivero, Daniel Heydecker
Firstly, we prove that, under some weak assumptions, vertex embeddings derived from random walks do indeed converge both in the single limit of the number of random walks $N \to \infty$ and in the double limit of both $N$ and the length of each random walk $L\to\infty$.