GGDiff casts conditional graph diffusion as stochastic optimal control and uses zero-order estimators to guide pre-trained models under differentiable and non-differentiable rewards.
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
-
Graph Guided Diffusion: Unified Guidance for Conditional Graph Generation
GGDiff casts conditional graph diffusion as stochastic optimal control and uses zero-order estimators to guide pre-trained models under differentiable and non-differentiable rewards.