REGE adds per-node uncertainty radii to graph embeddings and combines curriculum learning with conformal quantile regression to improve robustness to structural attacks.
Improving the general- izability of protein-ligand binding predictions with ai- bind,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 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.