AI Paper Atlas

Research map / Graph learning / GNN architectures

A Graph Meta-Network for Learning on Kolmogorov–Arnold Networks

Guy Bar-Shalom, Ami Tavory, Itay Evron, Maya Bechler-Speicher, Ido Guy, Haggai Maron

ICLR 2026 · Graph learning › GNN architectures · approach: Physics-inspired GNNs · 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
add bidirectional message passing (ablation)WS-KAN · INR classification CIFAR-10accuracy: 10.0 -> 42.2Improved
add bidirectional message passing (ablation)WS-KAN · INR classification F-MNISTaccuracy: 83.4 -> 84.6Improved
add bidirectional message passing (ablation)WS-KAN · Accuracy prediction MNISTMSE (x10^3): 4.03 -> 3.29Improved
add bidirectional message passing (ablation)WS-KAN · Accuracy prediction K-MNISTMSE (x10^3): 1.50 -> 1.45No clear effect
add bidirectional message passing (ablation)WS-KAN · Pruning mask prediction K-MNISTROC-AUC (%): 97.11 -> 99.46Improved
add positional encoding (ablation)WS-KAN · INR classification CIFAR-10accuracy: 46.1 -> 42.2Hurt
add positional encoding (ablation)WS-KAN · INR classification MNISTaccuracy: 94.3 -> 94.3No clear effect
add positional encoding (ablation)WS-KAN · Accuracy prediction MNISTMSE (x10^3): 2.53 -> 3.29Hurt
add positional encoding (ablation)WS-KAN · Pruning mask prediction K-MNISTaccuracy (%): 96.28 -> 97.72Improved
add permutation augmentation to MLP on flattened KAN parametersMLP · INR classification MNISTaccuracy: 34.1 -> 62.7Improved
add KAN alignment preprocessing to MLPMLP · INR classification MNISTaccuracy: 34.1 -> 81.0Improved
replace DeepSets over edges with the KAN-graph GNN (WS-KAN)DS · INR classification MNISTaccuracy: 59.1 -> 94.3Improved

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