AI Paper Atlas

Research map / Graph learning / GNN architectures

Understanding Truncated Positional Encodings for Graph Neural Networks

James Flora, Mitchell Black, Weng-Keen Wong, Amir Nayyeri

ICML 2026 · Graph learning › GNN architectures · approach: Weisfeiler-Leman expressivity hierarchies · 0 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 eigenspace projections k=3 instead of k=2 (ablation)k-EP-WL · BREC Totalaccuracy (%): 32 -> 46.5Improved
increase k-EP-WL from k=3 to k=7 (ablation)k-EP-WL · BREC Totalaccuracy (%): 46.5 -> 48Improved
use single biharmonic distance instead of k-EP-WL k=7k-harmonics · BREC Totalaccuracy (%): 48 -> 55Improved
use biharmonic instead of 4-harmonic (ablation)k-harmonics · BREC Totalaccuracy (%): 51 -> 55Improved
use biharmonic instead of resistance (ablation)k-harmonics · BREC CFIaccuracy (%): 7 -> 11Improved
compare single k-harmonic with 3-WL on CFI graphsk-harmonics · BREC CFIaccuracy (%): 60 -> 11Hurt
mix walks and k-harmonics (4+4) instead of k-harmonics alone (8) (ablation)k-harmonic PE · ZINC-12ktest MAE: 0.076 -> 0.064Improved
mix projections and walks (4+4) instead of projections alone (8) (ablation)projection PE · ZINC-12ktest MAE: 0.117 -> 0.075Improved
mix projections and walks (4+4) instead of walks alone (8) (ablation)walk PE · ZINC-12ktest MAE: 0.082 -> 0.075Improved
mix projections and k-harmonics (4+4) instead of projections alone (8) (ablation)projection PE · ZINC-12ktest MAE: 0.117 -> 0.078Improved
mix projections and k-harmonics (4+4) instead of k-harmonics alone (8) (ablation)k-harmonic PE · ZINC-12ktest MAE: 0.076 -> 0.078No clear effect
mix walks and k-harmonics (4+4) instead of walks alone (8) (ablation)walk PE · ZINC-12ktest MAE: 0.082 -> 0.064Improved

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