Search Results for author:
Found 2 papers, 2 papers with code
Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters
Both the jumps and the diffusion distances react to classification errors (i. e. they are learnable).
Ranked #1 on
Node Classification
on Chameleon
DiffWire: Inductive Graph Rewiring via the Lovász Bound
Graph Neural Networks (GNNs) have been shown to achieve competitive results to tackle graph-related tasks, such as node and graph classification, link prediction and node and graph clustering in a variety of domains.
Ranked #1 on
Graph Classification
on IMDB-BINARY
