Random Add-Drop Edge (RADE) jointly drops and adds edges stochastically during GNN training, with provable train-inference alignment and an adaptive rate balancer, to regularize against overfitting and mitigate over-squashing.
arXiv preprint arXiv:2106.05667 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RADE: Random Add-Drop Edge as a Regularizer
Random Add-Drop Edge (RADE) jointly drops and adds edges stochastically during GNN training, with provable train-inference alignment and an adaptive rate balancer, to regularize against overfitting and mitigate over-squashing.