AI Paper Atlas

Research map / Graph learning / GNN architectures

Graph Representational Learning: When Does More Expressivity Hurt Generalization?

Sohir Maskey, Raffaele Paolino, Fabian Jogl, Gitta Kutyniok, Johannes F. Lutzeyer

ICLR 2026 · Graph learning › GNN architectures · approach: Weisfeiler-Leman expressivity hierarchies · 1 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
add cycle-count features up to length 4 (F4-MPNN) to the MPNN (ablation)MPNN · Task 1 cycle-count labelstest accuracy: 0.8490 -> 0.9793Improved
use more expressive Local Folklore 2-GNN instead of F4-MPNN (ablation)F4-MPNN · Task 1 cycle-count labelstest accuracy: 0.9793 -> 0.8450Hurt
extend cycle features from length 4 to length 7 (ablation)F4-MPNN · Task 1 cycle-count labelstest accuracy: 0.9793 -> 0.9660Hurt
use fewer cycle features (length 3 only) than task requires (ablation)F4-MPNN · Task 1 cycle-count labelstest accuracy: 0.9793 -> 0.8657Hurt
increase distance of test graphs from the training set (zeta-TMD) (ablation)GIN on real-world datasets · BZR, Mutagenicity, NCI109accuracyHurt
destroy structure-label correlation via random label resampling (ablation)MPNN · BZR, Mutagenicity, NCI109test errorHurt

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