CMO adds a class-mean proximity constraint to distributionally robust optimization and NNR reweights graph samples by local label consistency, together improving minority-class accuracy in graph OOD experiments.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Robust OOD Graph Learning via Mean Constraints and Noise Reduction
CMO adds a class-mean proximity constraint to distributionally robust optimization and NNR reweights graph samples by local label consistency, together improving minority-class accuracy in graph OOD experiments.