Through a number of carefully chosen examples, we demonstrate that the isomorphic nature of graphs enables both the basic properties of data observed on graphs and their descriptors (features) to be ...

SIR-GCN emphasizes the anisotropic and dynamic (i.e., contextualized) transformation of neighborhood features to control and guide hash (aggregation) collisions when the space of node feature is ...

Our experiments show Census-Stub, which focuses on ‘stubs’ (half-edges), has orders of magnitude greater discerning power (ability to tell non-isomorphic graphs apart) than any other descriptor in ...

In the history of weird musical instrument interfaces, isomorphic keyboards are a favorite. These keyboards look like a grid of buttons, but when you play them, the relative shapes of chords are ...

This repo contains manually curated list of graph datasets for evaluation graph classification methods. These data sets are results of removing isomorphic copies of graphs from the original data sets.