AI Paper Atlas

Research map / Graph learning / GNN architectures

GLAD: Bidirectional Structure-Attribute Alignment via Latent Graph Diffusion Models

Jiankai Zuo, Yu Zhang, Yang Zhang, Zihao Yao, Yaying Zhang

ICML 2026 · Graph learning › GNN architectures · approach: Graph structure learning

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 backward topological alignment loss (lambda > 0) (ablation)GLAD · Cora, Citeseer, Amazon-C, Amazon-P attribute recoveryRecall@10: removal drops Recall@10 by nearly 30%Improved
add structure-aware classifier-free guidance at sampling (ablation)GLAD · Citeseer attribute recoveryRecall@kImproved
diffuse in decoupled latent spaces instead of a joint concatenated space (ablation)GLAD · four graph datasetsRecall@kImproved
replace adversarial alignment (SAT) with latent diffusion for sample diversityattribute completion · Cora, 80% missingaverage pairwise distance: 0.18 -> 1.12 (ground truth 1.18)Improved
add backward alignment so generated attributes reconstruct topologyattribute completion · Cora, 80% missinglink prediction AUC (%): 81.5% -> 88.4% vs WGNNImproved
use GLAD instead of SAT-GAT for node classification on Amazon-Photocompleted attributes · Amazon-Photoaccuracy (%): 92.50 -> 92.41No clear effect
use latent diffusion completion instead of GAN-based SAT for traffic ETAtraffic sensor networks · London ETAMAE: 97.74 -> 80.01Improved
use GLAD for congestion classification vs best baselinetraffic networks · Madrid, Melbourne, Londonaccuracy (%): Madrid 90.23 -> 93.38Improved

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