AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

HOG-Diff: Higher-Order Guided Diffusion for Graph Generation

Yiming Huang, Tolga Birdal

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 7 citations (OpenAlex)

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
use cell-based topological guide instead of Gaussian noise guide (ablation)HOG-Diff · QM9FCD: 0.829 -> 0.172Improved
use cell-based guide instead of noise guide (ablation)HOG-Diff · QM9Validity: 91.52 -> 98.74Improved
use cell-based guide instead of noise guide (ablation)HOG-Diff · QM9NSPDK: 0.0015 -> 0.0003Improved
use cell-based guide instead of peripheral guide (ablation)HOG-Diff · QM9FCD: 0.305 -> 0.172Improved
use cell-based guide instead of peripheral guide (ablation)HOG-Diff · QM9Validity: 97.58 -> 98.74Improved
use cell-based guide instead of noise guide (ablation)HOG-Diff · ZINC250kFCD: 1.665 -> 1.533Improved
use cell-based guide instead of peripheral guide (ablation)HOG-Diff · ZINC250kFCD: 1.541 -> 1.533Improved
use cell-based guide instead of noise guide (ablation)HOG-Diff · ZINC250kValidity: 96.78 -> 98.56Improved
use cell-based guide instead of peripheral guide (ablation)HOG-Diff · ZINC250kNSPDK: 0.002 -> 0.001No clear effect
coarse-to-fine higher-order guided bridge instead of classical noise diffusionHOG-Diff · spectrum loss trainingconvergence speedImproved
HOG-Diff vs DeFoG on curvature filtrationHOG-Diff · ZINC250kkappa_FR distance: 0.728 -> 0.190Improved
HOG-Diff vs Cometh on curvature filtrationHOG-Diff · SBMkappa_FR distance: 2.748 -> 1.453Improved

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