AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

FLAGG: Flexible Autoregressive Graph Generation

Samuel Cognolato, Alessandro Sperduti, Luciano Serafini

JMLR 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 DFS node ordering instead of BFS (ablation)Vanilla FLAGG {1,4} · QM9FCD: 0.144 -> 0.153Hurt
use random node ordering instead of BFS (ablation)Vanilla FLAGG {1,4} · QM9FCD: 0.144 -> 0.253Hurt
use random ordering instead of BFS (ablation)Vanilla FLAGG {1,4} · QM9Validity (%): 99.69 -> 99.72No clear effect
replace learned halting and insertion with empirical node-count sampling (ablation)FLAGG {1,3} · EnzymesDegree MMD: 0.048 -> 0.050Mixed
replace learned halting and insertion with empirical node-count sampling (ablation)FLAGG {1,2,8} · EnzymesGIN MMD: 0.048 -> 0.037Mixed
add property-based edge weights (P-FLAGG) to FLAGGFLAGG seq-small · EgoGIN MMD: 0.075 -> 0.037Improved
add property-based edge weights (P-FLAGG) to FLAGGFLAGG seq-small · Ego-smallGIN MMD: 0.031 -> 0.034Hurt
use large block sizes {1,4} instead of {1,2}FLAGG · QM9FCD: 0.212 -> 0.144Improved
use FLAGG improvements instead of IFH with intermediate sequentialityIFH {1,4,8} · ZINC250kValidity (%): 65.68 -> 97.81Improved
increase block size from seq-small to seq-bigFLAGG · EgoSampling time (minutes): 283.899 -> 67.213Improved
use properties FLAGG instead of seq-small FLAGG for sampling speedFLAGG · EgoSampling time (minutes): 283.899 -> 1.259Improved
reduce DiGress denoising steps by factor J=10 (ablation)FLAGG {1,4} · QM9Validity: validity over 99%No clear effect

Earlier methods this paper compares with

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