A reparameterized masked diffusion model with variational EM gives scalable structured node classification, matching or beating GNN, label propagation, and continuous diffusion baselines.
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
-
ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions
A reparameterized masked diffusion model with variational EM gives scalable structured node classification, matching or beating GNN, label propagation, and continuous diffusion baselines.