AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials

Guillem Simeon, Gianni De Fabritiis

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Scalable approximation and equivariant compute · 18 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 Cartesian rank-2 tensor representations in TensorNetmolecular potential prediction · QM9 U0MAE: 4.1 -> 3.9(1)Improved
use Cartesian rank-2 tensor representations in TensorNetmolecular potential prediction · QM9 GMAE: 5.5 -> 5.7(1)Hurt
use TensorNet instead of ETANI1x training and evaluation · ANI1xenergy MAE: 21.2 -> 17.3Improved
use TensorNet instead of ETANI1x-trained models · COMP6 ANI-MDenergy MAE: 249.7 -> 69.9Improved
remove interaction layers (ablation)TensorNet · rMD17 tolueneenergy MAE: 0.33 -> 3.3Hurt
add one interaction layer instead of none (ablation)TensorNet · rMD17 aspirinenergy MAE: 9.8 -> 2.7Improved
add a second interaction layer (ablation)TensorNet 1L, O(3), cutoff 4.5Å · rMD17 tolueneenergy MAE: 0.33 -> 0.26Improved
use SO(3) instead of O(3) equivariance (ablation)TensorNet 1L, cutoff 4.5Å · rMD17 aspirinforce MAE: 10.1 -> 13.1Hurt
increase cutoff from 4.5Å to 9Å (ablation)TensorNet 0L, O(3) · rMD17 tolueneenergy MAE: 3.3 -> 2.0Improved
increase cutoff from 4.5Å to 9Å (ablation)TensorNet 2L, O(3) · rMD17 tolueneenergy MAE: 0.26 -> 0.32Hurt
predict energy, forces, dipole, polarizability, and shielding jointlyTensorNet · Ethanol in vacuumdipole MAE: 0.003(0) vs 0.003No clear effect
use TensorNet instead of FieldSchNetethanol property prediction · Ethanol in vacuumenergy MAE: 0.017 -> 0.008(1)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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