Posts by Collection

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

Graph-based machine learning beyond stable materials and relaxed crystal structures

Published in Physical Review Materials, 2022

Evaluating the performance of a GNN for crystals in a high-throughput search setting, and proposing an ML-assisted workflow

Recommended citation: Ekström Kelvinius, F., Armiento, R., & Lindsten, F. (2022). Graph-based machine learning beyond stable materials and relaxed crystal structures. Physical Review Materials, 6(3), 033801.
Download Paper

Autoregressive Diffusion Models with non-Uniform Generation Order

Published in ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling, 2023

Investigating the generation order in autoregressive (diffusion) models for graph generation

Recommended citation: Kelvinius, F. E., & Lindsten, F. (2023). Autoregressive Diffusion Models with non-Uniform Generation Order. In ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling.
Download Paper

Accelerating Molecular Graph Neural Networks via Knowledge Distillation

Published in Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS 2023), 2023

Using knowledge distillation for improving performance of molecular graph neural networks

Recommended citation: Ekström Kelvinius, F., Georgiev, D., Toshev, A., & Gasteiger, J. (2024). Accelerating molecular graph neural networks via knowledge distillation. Advances in Neural Information Processing Systems, 36.
Download Paper | Download Slides

Discriminator Guidance for Autoregressive Diffusion Models

Published in The 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2024

Three versions of discriminator guidance for autoregressive (diffusion) models

Recommended citation: Ekström Kelvinius, F. & Lindsten, F.. (2024). Discriminator Guidance for Autoregressive Diffusion Models. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 238:3403-3411 Available from https://proceedings.mlr.press/v238/ekstrom-kelvinius24a.html.
Download Paper

Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo

Published in arXiv, 2025

Sequential Monte Carlo method for solving linear-Gaussian inverse problems with diffusion priors

Recommended citation: Ekström Kelvinius, F., Zhao, Z., & Lindsten, F. (2025). Solving Linear-Gaussian Bayesian Inverse Problems with Decoupled Diffusion Sequential Monte Carlo. arXiv preprint arXiv:2502.06379.
Download Paper

WyckoffDiff – A Generative Diffusion Model for Crystal Symmetry

Published in arXiv, 2025

Discrete diffusion model for generating materials as descriptions of their symmetry properties

Recommended citation: Ekström Kelvinius, F., Andersson, O. B., Parackal, A. S., Qian, D., Armiento, R., & Lindsten, F. (2025). WyckoffDiff-A Generative Diffusion Model for Crystal Symmetry. arXiv preprint arXiv:2502.06485.
Download Paper

Learning on Graphs and Geometry Meetup Uppsala

Published: February 12, 2025

Participated in the Learning on Graphs and Geometry meetup in Uppsala and presented our NeurIPS 2023 paper Accelerating Molecular Graph Neural Networks via Knowledge Distillation

TDAB01 Probability and Statistics

Undergraduate course, Linköping University, Division of Statistics and Machine Learning, 2021–present

A first course in probability and statistics for students on the engineering program in software engineering.

TDDE01/732A99 Machine Learning

Undergraduate course, Linköping University, Division of Statistics and Machine Learning, 2020–2022

Master’s level course in Machine Learning (TDDE01/732A99). Assisted in lab exercises and corrected exams.

TDDE70 Deep Learning

Undergraduate course, Linköping University, Division of Statistics and Machine Learning, 2024–present

Was part of the development of the new course in deep learning, given at the master’s level for engineering students for the first time in spring 2024. I was particurly involved in the development of the labs, and responsible for developing a lab on graph neural networks.

Master’s thesis supervision

Undergraduate course, Linköping University, Division of Statistics and Machine Learning, 2021–present

As a PhD student, I have been supervising 17 students in their master’s thesis work on topics related to machine learning. The students have been mainly from the Master’s program in Statistics and Machine Learning, but also the engineering programs in Computer Science and Engineering, Applied Physics and Electrical Engineering, and Industrial Engineering and Management.