Quest for new materials: Network theory and machine learning perspectives

Abstract

Understanding and predicting the emergence of novel materials is a fundamental challenge in condensed matter physics, materials science, and technology. With the rapid growth of materials databases in both size and reliability, the challenge shifts from data collection to efficient exploration of this vast and complex space. A key strategy lies in the smart use of descriptors at multiple scales, ranging from atomic arrangements to macroscopic properties, to represent materials in high-dimensional abstract spaces. Network theory provides a powerful framework to structure and analyze these relationships, capturing hidden patterns and guiding discovery. Machine learning complements this approach by enabling predictive modeling, dimensionality reduction, and the identification of promising material candidates. By integrating network-based methods with machine learning (ML) techniques, researchers can construct, analyze, and efficiently navigate the material space, uncovering novel materials with tailored properties. This review explores the synergy between network theory and ML, highlighting their role in accelerating materials discovery through a systematic and interpretable approach.