MoMa: A Simple Modular Learning Framework for Material Property Prediction

ICLR 2026 Conference Submission18965 Authors

Keywords: material property prediction, modular deep learning, AI4Materials

Abstract: Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train paradigm often fails to address the inherent diversity and disparity of material tasks. To overcome these challenges, we introduce MoMa, a simple 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.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 18965