About the Research
Research Theme
Machine learning for chemistry
Keyword
Generative machine learning, Geometric deep learning, Graph neural networks, Denoising diffusion, Energy-based models, Catalyst discovery, Transition state modeling
Research Outline
Having previously researched a variety of topics in different fields, including graph neural networks for catalyst discovery, here at ICReDD I will continue to research generative machine learning methods as applied in chemistry contexts, especially models trained on chemical reaction network data from AFIR search. Specifically, I will research machine learning methods such as energy-based models.
Representative Research Achievements
- A Deep Generative Model for the Inverse Design of Transition Metal Ligands and Complexes
Magnus Strandgaard, Trond Linjordet, Hannes Kneiding, Arron L. Burnage, Ainara Nova, Jan Halborg Jensen, David Balcells
JACS Au, 2025, 5, 2294-2308.
DOI: 10.1021/jacsau.5c00242 - Evolving Light Harvesting Metal Complexes with AI-Made Ligands
Alejandra Pita-Milleiro, Magnus Strandgaard, Trond Linjordet, Hannes Kneiding, David Balcells
ChemRxiv preprint, 2025.
DOI: 10.26434/chemrxiv-2025-23zrk - Towards Formally Grounded Evaluation Measures for Semantic Parsing-based Knowledge Graph Question Answering
Trond Linjordet, Krisztian Balog, Vinay Setty
ICTIR ’22: Proceedings of the 2022 ACM SIGIR International Conference on Theory of Information Retrieval, 2022, 3-12.
DOI: 10.1145/3539813.3545146 - Detecting Topological Entanglement Entropy in a Lattice of Quantum Harmonic Oscillators
Tommaso F. Demarie, Trond Linjordet, Nicolas C. Menicucci, Gavin K. Brennen
New Journal of Physics, 2014, 16.
DOI: 10.1088/1367-2630/16/8/085011