Viet-Anh on Software Logo

What is: DeepWalk?

SourceDeepWalk: Online Learning of Social Representations
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

DeepWalk learns embeddings (social representations) of a graph's vertices, by modeling a stream of short random walks. Social representations are latent features of the vertices that capture neighborhood similarity and community membership. These latent representations encode social relations in a continuous vector space with a relatively small number of dimensions. It generalizes neural language models to process a special language composed of a set of randomly-generated walks.

The goal is to learn a latent representation, not only a probability distribution of node co-occurrences, and so as to introduce a mapping function Φ ⁣:vVRV×d\Phi \colon v \in V \mapsto \mathbb{R}^{|V|\times d}. This mapping Φ\Phi represents the latent social representation associated with each vertex vv in the graph. In practice, Φ\Phi is represented by a V×d|V| \times d matrix of free parameters.