FastEGNN and DistEGNN use ordered, learnable virtual nodes with an MMD alignment loss to make equivariant GNNs accurate on sparse and distributed large geometric graphs.
Illuminating protein space with a programmable generative model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
Fast and Distributed Equivariant Graph Neural Networks by Virtual Node Learning
FastEGNN and DistEGNN use ordered, learnable virtual nodes with an MMD alignment loss to make equivariant GNNs accurate on sparse and distributed large geometric graphs.