Robust and Efficient AI Frameworks for Scalable Material Design and Property Prediction
cond-mat.mtrl-sci, cs.LG
Submitted: 2026-09-15
Updated: 2026-09-15
Code: https://github.com/kdmsit/crysxpp
License: http://creativecommons.org/licenses/by/4.0/
The gist: This thesis develops robust and efficient AI frameworks for accelerating crystalline materials discovery by addressing both major stages of the materials-design pipeline: crystal property prediction
Terminology
Abstract
This thesis develops robust and efficient AI frameworks for accelerating crystalline materials discovery by addressing both major stages of the materials-design pipeline: crystal property prediction and crystal structure generation. Motivated by the high computational cost of Density Functional Theory (DFT) and the limited availability of labeled materials data, the thesis explores graph representation learning, pretraining, multimodal learning, and generative modeling for scalable materials design. For property prediction, the thesis first introduces CrysXPP, which learns transferable crystal representations through unsupervised graph autoencoding, reducing dependence on large property-labeled datasets. It then proposes CrysGNN, a large-scale self-supervised graph pretraining framework that captures atomic connectivity, chemical attributes, and global structural information and transfers this knowledge to downstream property predictors through knowledge distillation. CrysMMNet further enriches crystal representations by jointly modeling graph structure and textual descriptions, thereby incorporating both local chemical and global structural knowledge. For crystal generation, the thesis introduces TGDMat, a text-guided joint diffusion framework that jointly models lattice parameters, atomic types, and atomic coordinates while incorporating textual structural knowledge during denoising. This enables the generation of more valid and stable periodic materials while also supporting conditional generation from natural-language descriptions. Overall, the thesis establishes a unified AI-based framework for data-efficient property prediction and controllable crystal generation, demonstrating how graph learning, multimodal representations, and generative models can reduce computational cost and improve the scalability of materials
Sources
- Equivariant Energy-Guided SDE for Inverse Molecular Design
- Graph Convolutional Matrix Completion
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Benchmarking Graph Neural Networks
- Text-Guided Molecule Generation with Diffusion Language Model
- Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
- Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
- Distilling the Knowledge in a Neural Network
- Data-Driven Approach to Encoding and Decoding 3-D Crystal Structures
- Efficient, Interpretable Graph Neural Network Representation for Angle-dependent Properties and its Application to Optical Spectroscopy
- Crystal Structure Prediction by Joint Equivariant Diffusion
- Space Group Constrained Crystal Generation
- All-atom Diffusion Transformers: Unified generative modelling of molecules and materials
- Adam: A Method for Stochastic Optimization
- AudioGen: Textually Guided Audio Generation
- GraphEBM: Molecular Graph Generation with Energy-Based Models
- Decoupled Weight Decay Regularization
- Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction
Related papers
- AES-Debye: an Accurate, Efficient, and Scalable Engine for Debye Scattering Calculations
- Cooperative Quantum Optical Effects of Moir'e Exciton Superlattices
- Imaging Surface Magnetization in Altermagnetic MnTe Films
- Accidental accuracy and formal consistency in GW +BSE: Exact benchmarks and regime-dependent error cancellation
- Modifying van der Waals Materials via Cavity Vacuum Fluctuations
- Linear dichroic soft X-ray microscopy of ferroelectric stripe domains in epitaxial K 0.6 Na 0.4 NbO 3