AI Paper Atlas

Research map / Graph learning / GNN architectures

On The Expressive Power of GNN Derivatives

Yam Eitan, Moshe Eliasof, Yoav Gelberg, Fabrizio Frasca, Guy Bar-Shalom, Haggai Maron

ICLR 2026 · Graph learning › GNN architectures · approach: Weisfeiler-Leman expressivity hierarchies · 2 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 analytic activation in base MPNN instead of non-analytic (ablation)HOD-GNN · synthetic substructure countingMAEImproved
use non-analytic activation instead of encoding-augmented MPNN (ablation)HOD-GNN · synthetic substructure countingMAEImproved
increase maximum derivative order up to 4 (ablation)HOD-GNN · synthetic substructure countingMAEImproved
increase maximum derivative order beyond 4 (ablation)HOD-GNN · synthetic substructure countingMAENo clear effect
change backbone MPNN among GCN, GIN, GPS (ablation)HOD-GNN · real-world datasetsaccuracy/MAENo clear effect
replace GIN + RWSE with HOD-GNNGIN + RWSE · ZINC-12KMAE: 0.128 -> 0.0666Improved
replace GCN + RWSE with HOD-GNNGCN + RWSE · Peptides-structMAE: 0.2574 -> 0.2450Improved
replace GIN with HOD-GNNGIN · ogbg-molhivROC-AUC: 75.58 -> 80.86Improved
use HOD-GNN instead of SubgraphormerSubgraphormer · ogbg-molbaceROC-AUC: 84.35 -> 82.10Hurt
use HOD-GNN instead of sampling-based Subgraph GNNs on PeptidesHyMN · Peptides-funcAP: 68.57 -> 69.68Improved

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