# Simultaneous Learning of Several Materials Properties from Incomplete Databases with Multi-Task SISSO

## TL;DR

This paper introduces a multi-task extension of the SISSO methodology to identify descriptors that predict multiple materials properties simultaneously, especially effective for incomplete and heterogeneous databases, aiding materials discovery.

## Contribution

The work extends SISSO to a multi-task learning framework, enabling simultaneous property prediction from incomplete datasets, which is novel in data-driven materials science.

## Key findings

- Successfully predicts multiple properties with a single descriptor.
- Effective handling of incomplete and partial data in materials databases.
- Demonstrated on stability and classification tasks for binary compounds.

## Abstract

The identification of descriptors of materials properties and functions that capture the underlying physical mechanisms is a critical goal in data-driven materials science. Only such descriptors will enable a trustful and efficient scanning of materials spaces and possibly the discovery of new materials. Recently, the sure-independence screening and sparsifying operator (SISSO) has been introduced and was successfully applied to a number of materials-science problems. SISSO is a compressed-sensing based methodology yielding predictive models that are expressed in form of analytical formulas, built from simple physical properties. These formulas are systematically selected from an immense number (billions or more) of candidates. In this work, we describe a powerful extension of the methodology to a 'multi-task learning' approach, which identifies a single descriptor capturing multiple target materials properties at the same time. This approach is specifically suited for a heterogeneous materials database with scarce or partial data, e.g., in which not all properties are reported for all materials in the training set. As showcase examples, we address the construction of materials-properties maps for the relative stability of octet-binary compounds, considering several crystal phases simultaneously, and the metal/insulator classification of binary materials distributed over many crystal-prototypes.