AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

An Efficient SE(p)-Invariant Transport Metric Driven by Polar Transport Discrepancy-based Representation

Junyi Lin, Dunyao Xue, Jun Yu, Hongteng Xu, Cheng Meng

ICLR 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport

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 SEINT regularization (alpha=0.3) to training lossUniGEM · QM9 pre-trainingmolecular stability (%): 89.4 -> 93.5Improved
add SEINT regularization (alpha=0.3) to training lossEDM · QM9 pre-trainingmolecular stability (%): 87.2 -> 91.5Improved
add SEINT regularization (alpha=0.3) to training lossEDM · QM9 pre-trainingvalidity (%): 93.4 -> 96.5Improved
add SEINT regularization (alpha=0.3) to training lossUniGEM · QM9 pre-trainingvalidity x uniqueness (%): 92.8 -> 91.8Hurt
replace L2-Norm coordinate loss with SEINT regularizer (alpha=0.1) (ablation)UniGEM · QM9 pre-trainingmolecular stability (%): 89.0 -> 91.0Improved
increase SEINT proportion from 0.1 to 0.3 (ablation)UniGEM · QM9 pre-trainingmolecular stability (%): 91.0 -> 93.5Improved
add L2-Norm coordinate regularizer (weight 0.2) (ablation)UniGEM · QM9 pre-trainingmolecular stability (%): 89.4 -> 85.3No clear effect
add SEINT regularizer (alpha=0.3) in fine-tuningUniGEM · QM9 fine-tuningmolecular stability (%): 89.4 -> 94.9Improved
add SEINT regularizer (alpha=0.3) in fine-tuningUniGEM · GEOM-Drugs fine-tuningmolecular stability (%): 1.2 -> 13.0Improved
add SEINT regularizer (alpha=0.3) in fine-tuningUniGEM · GEOM-Drugs fine-tuningvalidity (%): 98.3 -> 97.7Hurt
use SEINT instead of RISGW for rotation-invariant classificationkNN on distances · ModelNet40-SE(3)accuracy k=1: 74.9 -> 100.0Improved
use SEINT instead of GW for runtimedistance computation · ModelNet40-SE(3)CPU time (h): 2655.9 -> 9.01Improved

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