AI Paper Atlas

Research map / Graph learning / GNN architectures

LEAP: Local ECT-Based Learnable Positional Encodings for Graphs

Juan P Garcia Amboage, Ernst Röell, Patrick Schnider, Bastian Rieck

ICLR 2026 · Graph learning › GNN architectures · approach: Graph rewiring and scalable message passing · 1 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 LEAP positional encodingGCN/GAT on synthetic edge-count task · Synthetic edge-countaccuracy: 71.83 -> 100.0 (GCN)Improved
add LEAP-L PE to a GCNGCN · Letter-Haccuracy: 41.6 -> 74.2Improved
add LEAP-L to NoMP versus RWPENoMP · Letter-Haccuracy: 79.2 -> 81.6Improved
use 2-hop instead of 1-hop neighborhoods (ablation)LEAP-F · Letter-Haccuracy: 81.29 -> 74.44Hurt
concatenate 1-hop and 2-hop LEAP (ablation)LEAP-F · Letter-Haccuracy: 81.29 -> 77.91Hurt
learn directions instead of fixing them (ablation)LEAP (GCN, NoMP) · TU datasetsaccuracy: e.g. GCN Letter-H 72.2 -> 74.2Improved
learn directions instead of fixing them (ablation)LEAP with GAT · TU datasetsaccuracy: e.g. COX2 79.2 -> 80.1Mixed
vary PE dimension 2/5/10/20 (ablation)LEAP · Letter-H/M/L (NoMP)accuracy: Letter-H LEAP-F 81.16 (dim 2) vs 80.84 (dim 20)No clear effect
choice of projection strategy (linear, attention, DeepSets, 1D conv) (ablation)LEAP · TU datasetsaccuracy: GCN Letter-H LEAP-L 74.2 (linear) vs 62.7 (attn)Mixed
combine LEAP with LaPE on HIVGCN · HIVAUROCImproved
use LEAP instead of global DECT with CNNgraph classification · TU datasetsaccuracy: Letter-H 85.4 (DECT 65K) vs 74.2 (LEAP-L GCN)Mixed

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