A channel-permutation-equivariant GNN makes random noise usable as a general-purpose expressivity booster across graph tasks.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Using Random Noise Equivariantly to Boost Graph Neural Networks Universally
A channel-permutation-equivariant GNN makes random noise usable as a general-purpose expressivity booster across graph tasks.