Is Noise Conditioning Necessary? A Unified Theory of Unconditional Graph Diffusion Models

NeurIPSSpotlight2025

Authors: Jipeng Li, Yanning Shen
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Explicit noise-level conditioning is widely regarded as essential for the effective operation of Graph Diffusion Models (GDMs)

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

diffusion theory graph

← All NeurIPS 2025 Spotlight papers · Browse the whole archive