Beyond Structure: Invariant Crystal Property Prediction with Pseudo-Particle Ray Diffraction
This work solves the problem of accurate and efficient crystal property prediction for materials science researchers, offering a novel hybrid approach that improves over existing methods.
The paper tackled the problem of crystal property prediction by addressing limitations in graph-based models that fail to capture long-term atomic interactions, leading to inaccurate predictions. It introduced PRDNet, which uses reciprocal-space diffraction and pseudo-particles, achieving state-of-the-art performance on datasets like Materials Project, JARVIS-DFT, and MatBench.
Crystal property prediction, governed by quantum mechanical principles, is computationally prohibitive to solve exactly for large many-body systems using traditional density functional theory. While machine learning models have emerged as efficient approximations for large-scale applications, their performance is strongly influenced by the choice of atomic representation. Although modern graph-based approaches have progressively incorporated more structural information, they often fail to capture long-term atomic interactions due to finite receptive fields and local encoding schemes. This limitation leads to distinct crystals being mapped to identical representations, hindering accurate property prediction. To address this, we introduce PRDNet that leverages unique reciprocal-space diffraction besides graph representations. To enhance sensitivity to elemental and environmental variations, we employ a data-driven pseudo-particle to generate a synthetic diffraction pattern. PRDNet ensures full invariance to crystallographic symmetries. Extensive experiments are conducted on Materials Project, JARVIS-DFT, and MatBench, demonstrating that the proposed model achieves state-of-the-art performance.