Graffe uses a diffusion decoder conditioned on graph encoder outputs to learn node and graph representations, and it argues (with a flawed proof step) that the denoising objective is a lower bound on conditional mutual information.
Generative pretraining from pixels,
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
-
Graffe: Graph Representation Learning via Diffusion Probabilistic Models
Graffe uses a diffusion decoder conditioned on graph encoder outputs to learn node and graph representations, and it argues (with a flawed proof step) that the denoising objective is a lower bound on conditional mutual information.