A simplified hyperbolic GCN that avoids redundant log/exp computations is competitive or faster than prior HGCN variants on four benchmark graphs.
Scaled gromov hyperbolic graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
sHGCN: Simplified hyperbolic graph convolutional neural networks
A simplified hyperbolic GCN that avoids redundant log/exp computations is competitive or faster than prior HGCN variants on four benchmark graphs.