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

07/21/2021
by   Dominik Kloepfer, et al.
0

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 N →∞ and in the double limit of both N and the length of each random walk L→∞. 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.

READ FULL TEXT
research
10/26/2017

Watch Your Step: Learning Graph Embeddings Through Attention

Graph embedding methods represent nodes in a continuous vector space, pr...
research
05/20/2019

Random Walks on Hypergraphs with Edge-Dependent Vertex Weights

Hypergraphs are used in machine learning to model higher-order relations...
research
01/18/2021

Consistency of random-walk based network embedding algorithms

Random-walk based network embedding algorithms like node2vec and DeepWal...
research
12/01/2021

Efficient and Local Parallel Random Walks

Random walks are a fundamental primitive used in many machine learning a...
research
09/16/2019

Hipster random walks

We introduce and study a family of random processes on trees we call hip...
research
10/21/2020

Density of States Graph Kernels

An important problem on graph-structured data is that of quantifying sim...
research
04/13/2021

Optimal scaling of random walk Metropolis algorithms using Bayesian large-sample asymptotics

High-dimensional limit theorems have been shown to be useful to derive t...

Please sign up or login with your details

Forgot password? Click here to reset