Tag
This paper analyzes distance-preserving embeddings in inhomogeneous random graphs, providing tighter distortion bounds than classical worst-case results and introducing a GNN-augmented variant that learns universal features from small graphs.
MABLE combines masked reconstruction with cosine-similarity losses to learn node and graph embeddings from large heterogeneous graphs, demonstrated on geospatial mineral-exploration data. It unifies masked autoencoding and metric learning in a self-supervised framework without requiring labeled data.