Delving Into Deep Walkers: A Convergence Analysis of Random-Walk-Based Vertex Embeddings

arXiv2107.10014MaRDI QIDQ6373396FDOQ6373396

Authors: Dominik Kloepfer, Angelica I. Aviles-Rivero, Daniel Heydecker 

Publication date: 21 July 2021

Abstract: Graph vertex embeddings based on random walks have become increasingly influential in recent years, showing good performance in several tasks as they efficiently transform a graph into a more computationally digestible format while preserving relevant information. However, the theoretical properties of such algorithms, in particular the influence of hyperparameters and of the graph structure on their convergence behaviour, have so far not been well-understood. In this work, we provide a theoretical analysis for random-walks based embeddings techniques. 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 $Noinfty$ and in the double limit of both $N$ and the length of each random walk $Loinfty$. Secondly, we derive concentration bounds quantifying the converge rate of the corpora for the single and double limits. Thirdly, we use these results to derive a heuristic for choosing the hyperparameters $N$ and $L$. We validate and illustrate the practical importance of our findings with a range of numerical and visual experiments on several graphs drawn from real-world applications.

This page was built for publication: Delving Into Deep Walkers: A Convergence Analysis of Random-Walk-Based Vertex Embeddings

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6373396)