REGE adds per-node uncertainty radii to graph embeddings and combines curriculum learning with conformal quantile regression to improve robustness to structural attacks.
Graph-less neural networks: Teaching old mlps new tricks via distillation,
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
REGE: A Method for Incorporating Uncertainty in Graph Embeddings
REGE adds per-node uncertainty radii to graph embeddings and combines curriculum learning with conformal quantile regression to improve robustness to structural attacks.