AI Paper Atlas

Research map / Graph learning / GNN architectures

Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation

Luca Miglior, Matteo Tolloso, Alessio Gravina, Davide Bacciu

ICLR 2026 · Graph learning › GNN architectures · approach: GNN generalization theory · 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 global-attention transformer (GRIT) instead of local message passing (GCN)GNN on ECHO-Synth · ECHO-Synth sssptest MAE: 2.102 -> 0.121Improved
use GRIT instead of GCNGNN on ECHO-Synth · ECHO-Synth diamtest MAE: 3.832 -> 1.014Improved
use multi-hop rewiring (DRew) instead of GCNGNN on ECHO-Synth · ECHO-Synth ecctest MAE: 5.233 -> 4.651Improved
use non-dissipative dynamics (A-DGN) instead of GraphCONDE-GNN on ECHO-Synth · ECHO-Synth diamtest MAE: 2.969 -> 1.151Improved
use GPS instead of GCNGNN on ECHO-Energy · ECHO-Energytest MAE: 28.112 -> 5.257Improved
use SWAN instead of GINGNN on ECHO-Charge · ECHO-Charge (x1e-3)test MAE: 10.784 -> 6.109Improved
use GRIT instead of GPSgraph transformer on ECHO-Energy · ECHO-Energytest MAE: 5.257 -> 25.508Hurt
use GPS instead of GRITgraph transformer on ECHO-Synth · ECHO-Synth sssptest MAE: 0.121 -> 0.472Hurt
increase network depth (ablation)GNNs on ECHO · ECHOtest MAEImproved
vary readout depth (ablation)GNNs on ECHO · ECHOtest MAENo 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