AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Deep neural networks divide and conquer dihedral multiplication

Sihui Wei, Gavin McCracken, Gabriela Moisescu-Pareja, Harley Wiltzer, Doina Precup, Irina Rish, Jonathan Love

ICML 2026 · Graph learning › Graph algorithms and clustering · approach: Neural and local graph clustering

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
randomly permute the neuron cluster index before PCA/trace analysis (ablation)Cayley graph embedding · D18, 1000 seedsrotation trace |rho|: 0.9999 -> 0.0667Hurt
model each variable with a coupled first-order sinusoid rather than independent quadrant fitsneuron preactivation fit · D18 first layerR2: R2 avg = 0.9988Improved
increase group size n of DnMLP and transformer · D2 to D512number of neural representations: log fit a=1.79, b=0.726 (transformer); a=2.9, b=0.896 (MLP)Mixed
compare transformer to MLPCayley graph structure · D18coset clustering score: 0.993 -> 0.974Hurt
vary which reflection generator is used for a given Cayley graph (ablation)MLP · D18, 1000 seedsgenerator frequencyNo 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