GlobalWalk: Learning Global-aware Node Embeddings via Biased Sampling
This is an incremental improvement for graph learning tasks, addressing a known limitation in popular methods like DeepWalk.
The paper tackles the problem of node embedding methods omitting global graph information by proposing GlobalWalk, a biased random walk strategy that favors nodes with similar semantics, and empirical evidence shows it generally enhances global awareness in embeddings.
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.