DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
This work addresses the problem of high training costs and domain adaptation in materials discovery for researchers and engineers, representing a strong specific gain rather than a foundational advancement.
The paper tackles the challenge of fast and accurate property prediction for materials using Graph Neural Networks (GNNs) by introducing DenseGNN, which achieves state-of-the-art performance on datasets like JARVIS-DFT, Materials Project, and QM9, improving over models such as GIN, Schnet, and Hamnet.
Generative models generate vast numbers of hypothetical materials, necessitating fast, accurate models for property prediction. Graph Neural Networks (GNNs) excel in this domain but face challenges like high training costs, domain adaptation issues, and over-smoothing. We introduce DenseGNN, which employs Dense Connectivity Network (DCN), Hierarchical Node-Edge-Graph Residual Networks (HRN), and Local Structure Order Parameters Embedding (LOPE) to address these challenges. DenseGNN achieves state-of-the-art performance on datasets such as JARVIS-DFT, Materials Project, and QM9, improving the performance of models like GIN, Schnet, and Hamnet on materials datasets. By optimizing atomic embeddings and reducing computational costs, DenseGNN enables deeper architectures and surpasses other GNNs in crystal structure distinction, approaching X-ray diffraction method accuracy. This advances materials discovery and design.