Learning ORDER-Aware Multimodal Representations for Composite Materials Design

2026-01-23

arXiv.org

AI Summary

Traditional graph-centric approaches struggle to model the continuous, nonlinear design space of composite materials, and generic descriptors fail to effectively capture fiber distributions that govern performance, particularly under data scarcity. This work proposes ORDER, a novel framework that, for the first time, leverages ordinality as a core principle in multimodal representation learning. By integrating ordinal-aware image-tabular contrastive learning, latent space constraints, and physics-informed ordinal proxy signals, ORDER enables efficient pretraining without requiring complete performance labels. Evaluated on nanofiber-reinforced and T700 carbon fiber datasets, ORDER significantly outperforms existing methods across multiple tasks, including property prediction, cross-modal retrieval, and microstructure generation.

Abstract

Artificial intelligence (AI) has shown remarkable success in materials discovery and property prediction, particularly for crystalline and polymer systems where material properties and structures are dominated by discrete graph representations. Such graph-central paradigm breaks down on composite materials, which possess continuous and nonlinear design spaces that lack well-defined graph structures. General composite descriptors, e.g., fiber volume and misalignment angle, cannot fully capture the fiber distributions that fundamentally determine microstructural characteristics, necessitating the integration of heterogeneous data sources through multimodal learning. Existing alignment-oriented multimodal frameworks have proven effective on abundant crystal or polymer data under discrete, unique graph-property mapping assumptions, but fail to address the highly continuous composite design space under extreme data scarcity. In this work, we introduce ORDinal-aware imagE-tabulaR alignment (ORDER), a multimodal pretraining framework that establishes ordinality as a core principle for composite material representations. ORDER ensures that materials with similar target properties occupy nearby regions in the latent space, which effectively preserves the continuous nature of composite properties and enables meaningful interpolation between sparsely observed designs. We evaluate ORDER on a public Nanofiber-enforced composite dataset and an internally curated dataset that simulates the construction of carbon fiber T700 with diverse fiber distributions. ORDER achieves consistent improvements over state-of-the-art multimodal baselines across property prediction, cross-modal retrieval, and microstructure generation tasks.

Problem

• composite materials
• continuous design space
• multimodal learning
• data scarcity
• microstructural representation

Innovation

• ordinal-aware representation
• multimodal learning
• composite materials design
• data-efficient pretraining
• continuous design space