AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Roto-translated Local Coordinate Frames For Interacting Dynamical Systems

Miltiadis Kofinas, Naveen Shankar Nagaraja, Efstratios Gavves

NeurIPS 2021 · Graph learning › Knowledge and temporal graphs · approach: Heterogeneous graph learning · 4 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 roto-translated local coordinate frames (LoCS) instead of dNRI/NRI relation inferenceLoCS · Synthetic datasetrelation prediction F1: 60.8 -> 88.9Improved
evaluate on highly interactive charged-particle subset (ablation)LoCS · Charged particles high-intensity subsetMSEImproved
min-max normalization instead of speed normalization (ablation)LoCS · Synthetic datasetMSEHurt
add speed normalization (vs none) (ablation)LoCS · Synthetic datasetMSEImproved
speed normalization instead of min-max (ablation)dNRI · Synthetic datasetMSENo clear effect
anisotropic instead of isotropic filters (ablation)LoCS · inDMSEImproved
translation-only instead of roto-translated frames (ablation)LoCS · Charged particlesMSEHurt
LoCS vs dNRI, NRI, EGNN baselinesLoCS · Charged particles, inD, motion captureMSEImproved

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