AI Paper Atlas

Research map / Architectures and efficiency / CNN design

FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing

Ran Elbaz, Guy Bar-Shalom, Yam Eitan, Fabrizio Frasca, Haggai Maron

ICLR 2026 · Architectures and efficiency › CNN design · approach: Group symmetry equivariant networks · 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
use function-sharing KAN (FS-KAN) instead of DeepSets parameter-sharing MLPDeepSets · ModelNet40 continual learning, train size 200average accuracy: 0.380 -> 0.420Improved
use FS-KAN instead of DeepSetsDeepSets · ModelNet40 point clouds, train size 200 (acc. A1)accuracy: 0.514 -> 0.531Improved
use FS-KAN instead of DeepSetsDeepSets · ModelNet40, train size 1000average accuracy: 0.555 vs 0.553No clear effect
use FS-KAN instead of DeepSetsDeepSets · Forgetting at train size 200forgetting: 0.059 -> 0.034Improved
use FS-KAN instead of DeepSetsDeepSets · Forgetting at train size 1000forgetting: 0.027 -> 0.040Mixed
use efficient FS-KA layer instead of full FS-KA layer (ablation)FS-KAN · ModelNet40 continual learning avg accuracy, train size 200average accuracy: 0.420 -> 0.395Hurt
use efficient FS-KA layer instead of full (ablation)FS-KAN · ModelNet40 continual learning avg accuracy, train size 1000average accuracy: 0.553 -> 0.525Hurt
increase training data (high-data regime)FS-KAN vs parameter-sharing MLP · Rating prediction RMSERMSENo clear effect
share functions across symmetric edgesS_n-FS-KAN · synthetic invariant function (interpretability)interpretabilityImproved

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