Robust and Efficient AI Frameworks for Scalable Material Design and Property Prediction
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
Related
- Particle Inertia-Driven Pore Formation over Material Property Effects in Laser Powder-blown Directed Energy Deposition
- Scalable long-range machine learning interatomic potentials with electrical response for atomistic material modeling
- Efficient expectation value estimation for quantum circuits via extended stabilizer frameworks and adaptive variance estimation
- AES-Debye: an Accurate, Efficient, and Scalable Engine for Debye Scattering Calculations
- SmoQyElPhQMC.jl: An open-source Julia package for efficient and scalable quantum Monte Carlo simulations of electron-phonon coupled models
BibTeX
@misc{das2026robust,
title = {{Robust and Efficient AI Frameworks for Scalable Material Design and Property Prediction}},
author = {Kishalay Das},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.17646},
eprint = {2609.17646},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.17646},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Robust and Efficient AI Frameworks for Scalable Material Design and Property Prediction
AU - Kishalay Das
PY - 2026
DA - 2026/09/15
PB - arXiv
DO - 10.48550/arxiv.2609.17646
UR - https://arxiv.org/abs/2609.17646
AB - 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
ER -