LEED is a new local distance for GNNs that detects per-node over-smoothing and selects critical nodes for virtual-node-based graph rewiring.
Simplifying graph convolutional networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN
LEED is a new local distance for GNNs that detects per-node over-smoothing and selects critical nodes for virtual-node-based graph rewiring.