We propose a novel difference metric, called the graph diffusion distance (GDD), for quantifying the difference between two weighted graphs with the same number of vertices. Our approach is based on ...

Graphtools offers many additional options. For large graphs, you can speed up the powering of the diffusion matrix with landmarking: simply pass n_landmarks=1000 (e.g) when creating the graphtools ...

The success of graph neural networks (GNNs) largely relies on the process of aggregating information from neighbors defined by the input graph structures. Notably, message passing based GNNs, e.g., ...

We propose a novel difference metric, called the graph diffusion distance (GDD), for quantifying the difference between two weighted graphs with the same number of vertices. Our approach is based on ...