AI Paper Atlas

Research map / Graph learning / GNN architectures

LRIM: a Physics-Based Benchmark for Provably Evaluating Long-Range Capabilities in Graph Learning

Joël Mathys, Henrik Christiansen, Federico Errica, Takashi Maruyama, Francesco Alesiani

ICLR 2026 · Graph learning › GNN architectures · approach: GNN generalization theory

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
lower sigma from 1.5 to 0.6 (harder variant) (ablation)oracle predictor · LRIM oracle r-hop restrictionLogMSEHurt
increase system size L (ablation)oracle predictor · LRIM oracle r-hop restrictionLogMSEHurt
add more layers up to about 10 and 16 (ablation)MPNN and GPS baselines · LRIM-16-hard and LRIM-32-hardLogMSEImproved
add layers beyond roughly 10 (LRIM-16) and 16 (LRIM-32) (ablation)MPNN and GPS baselines · LRIM-16-hard and LRIM-32-hardLogMSENo clear effect
use graph transformer GPS-Base instead of GatedGCNbaseline · LRIM-16-hardLogMSE: -3.844 -> -4.211Improved
use GPS-Base instead of GatedGCNbaseline · LRIM-32-hardLogMSE: -4.087 -> -4.044No clear effect
add virtual node to GatedGCNGatedGCN · LRIM-16-hardLogMSE: -3.844 -> -4.068Improved
add virtual node to GatedGCNGatedGCN · LRIM-32-hardLogMSE: -4.087 -> -3.243Hurt
add RWSE encoding to GPSGPS-Base · LRIM-16-hardLogMSE: -4.211 -> -4.011Hurt
add LapPE encoding to GPSGPS-Base · LRIM-16-hardLogMSE: -4.211 -> -4.334Improved
transfer LRIM-16-hard model to LRIM-32-hard without retrainingGPS-Base · LRIM-32-hardLogMSE: -4.340 -> -1.057Hurt
transfer LRIM-16-hard model to LRIM-32-hard without retrainingGatedGCN · LRIM-32-hardLogMSE: -3.919 -> -1.050Hurt

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