AI Paper Atlas

Research map / Point clouds / Point cloud classification

Invariant and Equivariant Reynolds Networks

Akiyoshi Sannai, Makoto Kawano, Wataru Kumagai

JMLR 2024 · Point clouds › Point cloud classification · approach: Equivariant point cloud networks

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 Corner MSE loss instead of standard MSE loss (ablation)4-red ReyNet · Synthetic equivariant (n=5)MSE: 4.912e-5 -> 9.375e-5Hurt
use Corner MSE loss instead of standard MSE loss (ablation)4-red ReyNet · Synthetic equivariant (n=3)MSE: 1.438e-4 -> 1.249e-4Improved
use Corner MSE loss instead of standard MSE loss (ablation)4-red ReyNet · Synthetic equivariant (n=20)MSE: 1.608e-4 -> 8.537e-5Improved
add 4-reduction to ReyNetReyNet · Synthetic equivariant Symmetry (n=20)MSE: 3.151e-3 -> 6.554e-5Improved
replace IEGN with 4-red ReyNetIEGN · Synthetic equivariant Diagonal (n=20)MSE: 4.743e-4 -> 3.566e-5Improved
train on n=3 and test on larger input sizes4-red ReyNet · Synthetic Symmetry extrapolationMSEImproved
test invariant IEGN on larger input sizesIEGN · invariant tasks extrapolationgeneralizationHurt
use 4-red ReyNet instead of IEGNIEGN · MUTAGaccuracy: 78.33 ± 10 -> 89.44 ± 7.1Improved
use 4-red ReyNet-(i) instead of GINGIN · PTCaccuracy: 56.64 ± 7.0 -> 61.18 ± 5.2Improved
use 4-red ReyNet-(i) instead of IEGNIEGN · COLLABaccuracy: 78.12 ± 2.9 -> 73.62 ± 1.6Hurt
use larger hidden sizes (128, 256, 512) instead of (16, 16, 16) (ablation)4-red ReyNet · NCI1accuracy: 77.25 ± 2.0 -> 77.79 ± 2.1No clear effect
use ReyNet instead of GINGIN · MOL-HIVaccuracy: 0.7366 ± 0.0268 -> 0.7342 ± 0.0161No 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