Spectral Embedding of Graph Networks

Abstract

We introduce an unsupervised graph embedding that trades off local node similarity and connectivity, and global structure. The embedding is based on a generalized graph Laplacian, whose eigenvectors compactly capture both network structure and neighborhood proximity in a single representation. The key idea is to transform the given graph into one whose weights measure the centrality of an edge by the fraction of the number of shortest paths that pass through that edge, and employ its spectral proprieties in the representation. Testing the resulting graph network representation shows significant improvement over the sate of the art in data analysis tasks including social networks and material science. We also test our method on node classification from the human-SARS CoV-2 protein-protein interactome.

References in corpus (7)

• Community structure in social and biological networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Learning Structural Node Embeddings Via Diffusion Wavelets
• A Spectral Graph Uncertainty Principle
• Detection of Core-Periphery Structure in Networks Using Spectral Methods and Geodesic Paths
• Forecasting failure locations in two-dimensional disordered lattices
• Rigidity percolation control of the brittle-ductile transition in disordered networks