Theoretical and Computational Chemistry

Euclidean Symmetry and Equivariance in Machine Learning

Tess Smidt Lawrence Berkeley National Laboratory


Understanding symmetry’s role in the physical sciences is critical for choosing an appropriate machine learning method. While invariant models are the most prevalent symmetry-aware models, equivariant models can more faithfully represent physical interactions. Until recently, equivariant models had been absent in the literature due to their technical complexity. Now, after two years of active development, fully-equivariant Euclidean neural net- works are ready to take on challenges across the physical sciences.


Thumbnail image of Trends_in_Chem_Forum_Euclidean_Symmetry_and_Equivariance_in_ML_20200909.pdf
download asset Trends_in_Chem_Forum_Euclidean_Symmetry_and_Equivariance_in_ML_20200909.pdf 7 MB [opens in a new tab]