Not stated in source
2026 Needs review
Efficient Graph Neural Networks for Predicting Chemistry
Abstract
Graph Neural Networks (GNNs) are powerful deep learning models for predicting molecular properties but they require large datasets and significant computational resources. My research focuses on enhancing their efficiency and accuracy by improving how these models learn and process information internally. By inventing new model architectures and training strategies, I demonstrate that GNNs can achieve superior prediction accuracy while using either the same or even fewer computational resources. My work advances the development of efficient GNNs for chemistry prediction.
Keywords
Not available
Specialisations
Similar theses
- Simultaneous Shape, Size, and Topology Optimization of Truss Structures Using Graph Neural Networks and Metaheuristic Algorithms Ali Mosalli · 2026
- The expressivity and explainability of graph neural networks Matthew Morris · University of Oxford · 2026
- On the Adversarial Robustness of Graph Neural Networks Sofiane Ennadir · Dalarna University Library · 2026
- Causal Inference Explanations for Graph Neural Networks Sahil Satish Kumar · 2025
- Network anomaly detection with graph neural networks Hamid Latif-Martínez · Universitat Politècnica de Catalunya · 2025
- Using spatial data in graph neural networks Artem Kopyl · 2025
