DG-Gen directly models the probability of temporal edges as a product of conditional distributions and autoregressively generates continuous-time dynamic graphs with node and edge features.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generation
DG-Gen directly models the probability of temporal edges as a product of conditional distributions and autoregressively generates continuous-time dynamic graphs with node and edge features.