AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Rotary Position Encodings for Graphs

Isaac Reid, Arijit Sehanobish, Cederik Höfs, Bruno Kacper Mlodozeniec, Leonhard Vulpius, Federico Barbero, Adrian Weller, Krzysztof Marcin Choromanski, Richard E. Turner, Petar Veličković

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning

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 WIRE rotary encodings with m=5 spectral coordinatesTransformer · Shortest path distance, Watts-Strogatztest RMSE: 0.065(5) -> 0.038(6)Improved
increase spectral coordinates from m=5 to m=10 (ablation)Transformer + WIRE · Shortest path distance, Watts-Strogatztest RMSE: 0.038(6) -> 0.045(4)No clear effect
add WIRE (m=10) to the transformerTransformer · Monochromatic subgraph, 5 edges deletednormalised test RMSE: 0.087(1) -> 0.068(5)Improved
add WIRE with only m=3 coordinates when graph is far from grid (ablation)Transformer · Monochromatic subgraph, 15 edges deletednormalised test RMSE: 0.068(2) -> 0.064(3)No clear effect
increase m from 3 to 10 on more irregular graphs (ablation)Transformer + WIRE · Monochromatic subgraph, 5 edges deletednormalised test RMSE: 0.075(2) -> 0.068(5)Improved
add WIRE to PerformerGraphGPS Performer · MNISTaccuracy: 97.56(2) -> 98.10(1)Improved
add WIRE to PerformerGraphGPS Performer · ogbg-molpcbatest metric: 0.238(3) -> 0.264(1)Improved
add WIRE to PerformerGraphGPS Performer · ogbg-code2test metric: 0.1731(9) -> 0.1733(9)No clear effect
add WIRE to PerformerGraphGPS Performer · ogbg-ppatest metric: 0.8009(8) -> 0.804(2)No clear effect
add WIRE to PerformerGraphGPS Performer · MalNet-Tinyaccuracy: 92.81(5) -> 93.46(2)Improved
add WIRE to PerformerGraphGPS Performer · Peptides-structtest metric (MAE): 0.2616(4) -> 0.2566(4)Improved
add gauge-invariance handling (SignNet etc.) to WIREWIRE · synthetic and benchmark tasksperformanceNo 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