Graph sampling for node embedding
This addresses efficiency challenges in graph learning for researchers and practitioners, but appears incremental as it builds on existing sampling and embedding methods.
The paper tackles the problem of computational efficiency and scalability in node embedding for graph representation learning by proposing sampling approaches that extract information from graph Laplacian eigenvectors and given values, aiming to improve performance without specifying concrete results.
Node embedding is a central topic in graph representation learning. Computational efficiency and scalability can be challenging to any method that requires full-graph operations. We propose sampling approaches to node embedding, with or without explicit modelling of the feature vector, which aim to extract useful information from both the eigenvectors related to the graph Laplacien and the given values associated with the graph.