AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Feature-Aware (Hyper)graph Generation via Next-Scale Prediction

Dorian Gailhard, Enzo Tartaglione, Lirida Naviner, Jhony H. Giraldo

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation · 0 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 hierarchical scale encoding instead of concatenating target size to node embeddings (ablation)FAHNES · ModelNet BookshelfNode Num: 0.940±0.917 -> 0.135±0.276Improved
use hierarchical scale encoding (ablation)FAHNES · ModelNet PianoNode Num: 3.622±1.822 -> 0.846±1.009Improved
use hierarchical scale encoding (ablation)FAHNES · ManifoldNet AirplaneChamDist: 0.079±0.019 -> 0.048±0.003Improved
add multi-scale graph OT coupling (ablation)FAHNES · ManifoldNet AirplaneChamDist: 0.050±0.005 -> 0.048±0.003No clear effect
add multi-scale graph OT coupling (ablation)FAHNES · ManifoldNet BenchChamDist: 0.085±0.056 -> 0.064±0.005Improved
add multi-scale graph OT coupling (ablation)FAHNES · ModelNet BookshelfSpectral: 0.014±0.007 -> 0.024±0.015Hurt
remove both scale encoding and OT coupling (ablation)FAHNES · ModelNet PianoNode Num: 5.490±8.847 -> 0.846±1.009Improved
joint topology and feature generation instead of sequential topology-then-featuresFAHNES · ManifoldNet AirplaneChamDist: 0.082±0.074 -> 0.048±0.003Improved
hierarchical generation instead of flat modelsgraph point cloud datasets · Airplane Point CloudsChamDist: OOM for flat baselines -> 0.094±0.006Improved
use FAHNES instead of flat DeFoG on small SBM graphsDeFoG · SBM graphsValid (%): 90.0±5.1 -> 50.0±5.0Hurt
use FAHNES instead of HSpectre on unfeatured graphsHSpectre · Point cloud graphsRatio: 7.0 -> 3.2±0.5Improved
use FAHNES instead of HYGENE on featureless hypergraphsHYGENE · SBM hypergraphsValid (%): 65.0 -> 87.8±3.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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