Adaptive random walks that climb coarsened hierarchical levels beat the theoretical accuracy bound for walks on the original graph, reaching long-range information with shorter walks.
Graph neural networks with learnable structural and positional representations,
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Learn to Jump: Adaptive Random Walks for Long-Range Propagation through Graph Hierarchies
Adaptive random walks that climb coarsened hierarchical levels beat the theoretical accuracy bound for walks on the original graph, reaching long-range information with shorter walks.