AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Global and Local Topology-Aware Graph Generation via Dual Conditioning Diffusion

Yuhang Xie, Sinno Jialin Pan

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation

Read the paperCheck your idea against 137,217 papers

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
add self-conditioning (ablation)DualDiff · ZINC250kFCD: 0.65 -> 0.72Improved
add self-conditioning (ablation)DualDiff · ZINC250kKL: 0.82 -> 0.89Improved
replace self-conditioning with full dual conditioning (ablation)DualDiff · ZINC250kFCD: 0.72 -> 0.91Improved
replace self-conditioning with full dual conditioning (ablation)DualDiff · ZINC250kKL: 0.89 -> 0.98Improved
add global-to-local conditioning to local-to-global-only conditioning (full dual) (ablation)DualDiff · ZINC250kFCD: 0.75 -> 0.91Improved
add local-to-global conditioning to global-to-local-only conditioning (full dual) (ablation)DualDiff · ZINC250kFCD: 0.83 -> 0.91Improved
add dual conditioning (ablation)DualDiff · QM9 sampling time for 10,000 graphssampling time (s): 32 -> 41Hurt
add dual conditioning (ablation)DualDiff · ZINC250k sampling time for 10,000 graphssampling time (s): 169 -> 223Hurt
use DualDiff instead of GDSSsampling · ZINC250k sampling timesampling time (s): 1870 -> 223Improved
increase diffusion steps from 50 to 1000 (ablation)DualDiff · Community-smallMMD: 0.098 -> 0.006Improved
use DualDiff instead of hierarchical PPGNgeneric graph generation · PlanarOrbit MMD: 0.0006 -> 0.0002Improved
use DualDiff instead of hierarchical HiGengeneric graph generation · SBMOrbit MMD: 0.0604 -> 0.0365Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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