Fig. 2: The graph design space for generating random graphs.
From: Exploring robust architectures for deep artificial neural networks
a–c Show 2.313 M candidate graphs from Watts–Strogatz flex generator downsampled to 3854 and 54 graphs. d, e Show 3854 and 54 graphs in a 3-D space spanned by clustering coefficient (C), path length (L), and entropy (H). Samples of the complete and sparse graphs are identified in (a) and (e).
