MoMa: A Modular Deep Learning Framework for Material Property Prediction

TL;DR

MoMa is a modular deep learning framework that trains specialized modules for material property prediction and adaptively composes them for specific tasks, achieving significant improvements over existing methods.

Contribution

Introduces MoMa, a novel modular framework that enhances material property prediction by training and composing specialized modules for diverse tasks.

Findings

14% average improvement over baselines

Effective in few-shot learning scenarios

Demonstrates versatility across 17 datasets

Abstract

Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train then fine-tune paradigm often fails to address the inherent diversity and disparity of material tasks. To overcome these challenges, we introduce MoMa, a Modular framework for Materials that first trains specialized modules across a wide range of tasks and then adaptively composes synergistic modules tailored to each downstream scenario. Evaluation across 17 datasets demonstrates the superiority of MoMa, with a substantial 14% average improvement over the strongest baseline. Few-shot and continual learning experiments further highlight MoMa's potential for real-world applications. Pioneering a new paradigm of modular material learning, MoMa will be open-sourced to foster broader community collaboration.