Revisiting the Canonicalization for Fast and Accurate Crystal Tensor Property Prediction

TL;DR

This paper introduces GoeCTP, a novel framework that uses canonicalization via polar decomposition to efficiently predict crystal tensor properties with high accuracy, significantly reducing computational costs.

Contribution

It presents a general O(3)-equivariant framework leveraging canonicalization for fast, accurate tensor property prediction without complex architectural constraints.

Findings

GoeCTP achieves up to 13 times faster predictions.

It maintains high accuracy comparable to state-of-the-art methods.

The framework simplifies tensor equivariant learning using canonicalization.

Abstract

Predicting the tensor properties of crystalline materials is a fundamental task in materials science. Unlike scalar property prediction, which requires invariance, tensor property prediction requires maintaining O(3) group tensor equivariance. Achieving such equivariance typically demands specialized architectural designs, which substantially increase computational cost. Canonicalization, a classical technique for geometry, has recently been explored for efficient learning with symmetry.In this work, we revisit the problem of crystal tensor property prediction through the lens of canonicalization. Specifically, we demonstrate how polar decomposition, a simple yet efficient algebraic method, can serve as a form of canonicalization and be leveraged to ensure equivariant tensor property prediction. Building upon this insight, we propose a general O(3)-equivariant framework for fast and accurate crystal tensor property prediction, referred to as GoeCTP. By utilizing canonicalization, GoeCTP achieves high efficiency without requiring the explicit incorporation of equivariance constraints into the network architecture.Experimental results indicate that GoeCTP achieves the high prediction accuracy and runs up to 13 times faster compared to existing state-of-the-art methods, underscoring its effectiveness and efficiency.