Local Graph Embeddings Based on Neighbors Degree Frequency of Nodes

TL;DR

This paper introduces local node embeddings based on neighbors' degree frequency, extending to dynamic and directed graphs, and demonstrates their effectiveness in learning centrality measures via deep neural networks.

Contribution

It proposes the neighbors degree frequency (NDF) embedding and matrix representations for nodes, enabling local-to-global graph analysis and isomorphism testing with deep learning.

Findings

NDF embeddings encode local neighborhood structure.

Deep learning can predict PageRank and closeness centrality from embeddings.

Method handles dynamic and directed graphs effectively.

Abstract

We propose a local-to-global strategy for graph machine learning and network analysis by defining certain local features and vector representations of nodes and then using them to learn globally defined metrics and properties of the nodes by means of deep neural networks. By extending the notion of the degree of a node via Breath-First Search, a general family of {\bf parametric centrality functions} is defined which are able to reveal the importance of nodes. We introduce the {\bf neighbors degree frequency (NDF)}, as a locally defined embedding of nodes of undirected graphs into euclidean spaces. This gives rise to a vectorized labeling of nodes which encodes the structure of local neighborhoods of nodes and can be used for graph isomorphism testing. We add flexibility to our construction so that it can handle dynamic graphs as well. Afterwards, the Breadth-First Search is used to extend NDF vector representations into two different matrix representations of nodes which contain higher order information about the neighborhoods of nodes. Our matrix representations of nodes provide us with a new way of visualizing the shape of the neighborhood of a node. Furthermore, we use these matrix representations to obtain feature vectors, which are suitable for typical deep learning algorithms. To demonstrate these node embeddings actually contain some information about the nodes, in a series of examples, we show that PageRank and closeness centrality can be learned by applying deep learning to these local features. Our constructions are flexible enough to handle evolving graphs. Finally, we explain how to adapt our constructions for directed graphs.