AI Paper Atlas

Research map / Graph learning / GNN architectures

Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement

Huidong Liang, Haitz Sáez de Ocáriz Borde, Baskaran Sripathmanathan, Michael M. Bronstein, Xiaowen Dong

ICLR 2026 · Graph learning › GNN architectures · approach: GNN generalization theory · 14 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 graph message passing instead of node features alone (MLP to GraphSAGE)MLP · City-Networks Paristest accuracy: 25.5 -> 54.6Improved
add geographic coordinates to node features (ablation)Exphormer · City-Networks Paristest accuracy: 53.5 -> 55.1Improved
add geographic coordinates to node features (ablation)GraphSAGE · City-Networks Shanghaitest accuracy: 66.5 -> 68.3Improved
add the other node features and graph to coordinates (ablation)MLP coordinates only · City-Networks Paristest accuracy: 12.5 -> 25.5Improved
increase number of message-passing layers from 2 to 16GNNs and GTs · City-Networkstest accuracyImproved
increase number of message-passing layersGNNs and GTs · Cora and ogbn-arxivtest accuracyHurt
increase number of message-passing layersGNNs and GTs · Amazon-Ratings and PascalVOC-SPtest accuracyNo clear effect
raise label locality k from 8 to 16 or 32 (ablation)GCN · City-Networks Parislayers needed to plateau: saturates at num_layers 8 -> plateaus at num_layers 16Improved
raise layers from 16 to 32 at k=32 (ablation)GCN · City-Networks Paristest accuracyNo clear effect
use Exphormer instead of GCNGCN · City-Networks Shanghaitest accuracy: 62.1 -> 70.2Improved
add GraphGPS global attention on LondonGraphGPS · City-Networks Londontest accuracy: OOMHurt

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