Continuous-time dynamic GNNs built from static universal approximators and recurrent updates match a new continuous-time 1-WL test and inherit universal approximation guarantees, even on disconnected asynchronous graphs.
IEEE Transactions on Neural Networks 20(1), 81–102 (2008)
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
-
Weisfeiler-Lehman meets Events: An Expressivity Analysis for Continuous-Time Dynamic Graph Neural Networks
Continuous-time dynamic GNNs built from static universal approximators and recurrent updates match a new continuous-time 1-WL test and inherit universal approximation guarantees, even on disconnected asynchronous graphs.