GlobalWalk: Learning Global-aware Node Embeddings via Biased Sampling

TL;DR

GlobalWalk introduces a biased random walk strategy that enhances global semantic awareness in node embeddings, addressing the limitations of traditional methods that focus mainly on local topology.

Contribution

It proposes a novel biased sampling method for random walks that incorporates global semantic information into node embeddings.

Findings

GlobalWalk improves global awareness of node embeddings.

Enhanced embeddings lead to better performance in downstream tasks.

Biased sampling effectively captures global semantic relationships.

Abstract

Popular node embedding methods such as DeepWalk follow the paradigm of performing random walks on the graph, and then requiring each node to be proximate to those appearing along with it. Though proved to be successful in various tasks, this paradigm reduces a graph with topology to a set of sequential sentences, thus omitting global information. To produce global-aware node embeddings, we propose GlobalWalk, a biased random walk strategy that favors nodes with similar semantics. Empirical evidence suggests GlobalWalk can generally enhance global awareness of the generated embeddings.