AI Paper Atlas

Research map / Graph learning / GNN architectures

Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning

Yi Huang, Qingyun Sun, Jia Li, Xingcheng Fu, Jianxin Li

ICML 2026 · Graph learning › GNN architectures · approach: Structural GNN variants · 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
learn table roles (node vs edge) jointly with the GNN (FROG) instead of fixed schema graphRDL GraphSAGE / RelGNN · rel-event user-ignoreROC-AUC: 82.55 -> 85.49 (vs RelGNN)Improved
learn table roles instead of fixed roles on rel-hm item-sales regressionRDL GraphSAGE · rel-hm item-salesMAE: 0.0556 (RDL) vs 0.0561 (FROG)No clear effect
learn table roles (FROG) on rel-trial study-adverseLightGBM · rel-trial study-adverseMAE: 42.8452 (LightGBM) vs 44.7536 (FROG)Hurt
learn table roles on site-sponsor-run recommendationRelGNN · rel-trial site-sponsor-runMAP: 19.10 (RelGNN) vs 19.09 (FROG)No clear effect
learned node/edge role mixing versus all-node, all-edge, or random weights (ablation)FROG table roles · rel-event user-repeat, rel-avito ad-ctr, rel-stack post-post-relatedROC-AUC / MAE / MAPImproved
model all tables as nodes vs all as edges (ablation)FROG variants · rel-event user-repeat vs rel-avito ad-ctrROC-AUC / MAEMixed
add functional dependency losses L_emb and L_pair (ablation)FROG representations · rel-event, rel-avito (embedding visualization)embedding separability (qualitative)Improved
transfer structure learned from other tasks (rel-event user-repeat) (ablation)FROG · rel-event user-repeatROC-AUC: 79.01 -> 76.30 / 74.31Hurt
transfer structure learned from other tasks (rel-event user-attendance) (ablation)FROG · rel-event user-attendanceMAE: 0.2435 vs 0.2635Improved
transfer structures across rel-avito tasks (ablation)FROG · rel-avitoROC-AUC / MAE / MAP: user-visits 66.37 vs 66.54 transferredNo clear effect

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