Multimodal Foundation Models for Material Property Prediction and Discovery
arXiv:2312.00111 · doi:10.1016/j.newton.2025.100016
Abstract
Artificial intelligence is transforming computational materials science, improving the prediction of material properties, and accelerating the discovery of novel materials. Recently, publicly available material data repositories have grown rapidly. This growth encompasses not only more materials but also a greater variety and quantity of their associated properties. Existing machine learning efforts in materials science focus primarily on single-modality tasks, i.e. relationships between materials and a single physical property, thus not taking advantage of the rich and multimodal set of material properties. Here, we introduce Multimodal Learning for Materials (MultiMat), which enables self-supervised multi-modality training of foundation models for materials. We demonstrate our framework's potential using data from the Materials Project database on multiple axes: (i) MultiMat achieves state-of-the-art performance for challenging material property prediction tasks; (ii) MultiMat enables novel and accurate material discovery via latent space similarity, enabling screening for stable materials with desired properties; and (iii) MultiMat encodes interpretable emergent features that may provide novel scientific insights.
12 pages, 4 figures
References in corpus (26)
- Representation Learning with Contrastive Predictive Coding
- Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
- SchNet - a deep learning architecture for molecules and materials
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- On the Opportunities and Risks of Foundation Models
- A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
- Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
- The (High Quality) Topological Materials In The World
- BerkeleyGW: A Massively Parallel Computer Package for the Calculation of the Quasiparticle and Optical Properties of Materials and Nanostructures
- Big Data of Materials Science - Critical Role of the Descriptor
- Catalogue of Topological Electronic Materials
- Gemini: A Family of Highly Capable Multimodal Models
- Align before Fuse: Vision and Language Representation Learning with Momentum Distillation
- Towards ideal topological materials: Comprehensive database searches using symmetry indicators
- Atomistic Line Graph Neural Network for Improved Materials Property Predictions
- CoCa: Contrastive Captioners are Image-Text Foundation Models
- A Map of the Inorganic Ternary Metal Nitrides
- Interpretable and Explainable Machine Learning for Materials Science and Chemistry
- Florence: A New Foundation Model for Computer Vision
- Towards self-driving laboratories: The central role of density functional theory in the AI age
- Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings
- Representing individual electronic states for machine learning GW band structures of 2D materials
- Periodic Graph Transformers for Crystal Material Property Prediction
- LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions
- Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials
- VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment