AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Discrete Bayesian Sample Inference for Graph Generation

Ole Petersen, Marcel Kollovieh, Marten Lienen, Stephan Günnemann

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 0 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase noise level gamma from 0 (probability flow ODE) to tuned values (ablation)GraphBSI · MosesSNN, Filters, FCDImproved
use Ornstein-Uhlenbeck instead of Euler-Maruyama discretization at high noise (ablation)GraphBSI · Mosessample qualityImproved
finer discretization at later timesteps (rho<1) (ablation)GraphBSI · MosesFCDImproved
non-uniform timestepping rho (ablation)GraphBSI · MosesSNN, FiltersNo clear effect
exponential instead of linear precision schedule (ablation)GraphBSI · Moseskey metricsNo clear effect
set final precision just high enough for perfect reconstruction (ablation)GraphBSI · Moseskey metricsImproved
increase initial variance beta_0 from 0.05 to 1.0 (ablation)OU sampler vs Flowback sampler · Moseskey metricsMixed
increase compute budget (NFEs 25 to 500) (ablation)GraphBSI · MosesnoveltyHurt
gamma to infinity sampler (Flowback-like) with higher budget (ablation)GraphBSI · Mosesmolecule metricsMixed
use EM sampler at 500 stepsGraphBSI · MosesFCD: 1.07 -> 0.72Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy