Convergence Guarantees for the DeepWalk Embedding on Block Models
Preprint
Abstract
Graph embeddings have emerged as a powerful tool for understanding the structure of graphs. Unlike classical spectral methods, recent methods such as DeepWalk, Node2Vec, etc. are based on solving nonlinear optimization problems on the graph, using local information obtained by performing random walks. These techniques have empirically been shown to produce ''better'' embeddings than their classical counterparts. However, due to their reliance on solving a nonconvex optimization problem, obtaining theoretical guarantees on the properties of the solution has remained a challenge, even for simple classes of graphs. In this work, we show convergence properties for the DeepWalk algorithm on graphs obtained from the Stochastic Block Model (SBM). Despite being simplistic, the SBM has proved to be a classic model for analyzing the behavior of algorithms on large graphs. Our results mirror the existing ones for spectral embeddings on SBMs, showing that even in the case of one-dimensional embeddings, the output of the DeepWalk algorithm provably recovers the cluster structure with high probability.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Clustering with t-SNE, ProvablySIAM Journal on Mathematics of Data Science, 2019
- Spectral clustering and the high-dimensional stochastic blockmodelThe Annals of Statistics, 2011
- Expander flows, geometric embeddings and graph partitioningJournal of the ACM, 2009
- Approximate counting, uniform generation and rapidly mixing Markov chainsInformation and Computation, 1989
- Eigenvalues and expandersCombinatorica, 1986
- Stochastic blockmodels: First stepsSocial Networks, 1983
- An r-Dimensional Quadratic Placement AlgorithmManagement Science, 1970