Photo of Joel Oskarsson

Joel Oskarsson

PhD student

My research interests are in spatio-temporal and graph-based machine learning.

Presentation

I am a PhD-student at the Division of Statistics and Machine Learning. My main supervisor is Fredrik Lindsten and co-supervisors Per Sidén and Jose M. Peña. I am an affiliated PhD-student within the WASP program.

Research

In my research I aim to develop machine learning methods for structured data. I develop methods for data with spatial-, temporal- and graph-structure, including combinations of these. In particular, I am interested in how more traditional probabilistic methods in these domains can be combined with deep learning in order to derive new methods with useful properties.

For more information, please visit my webpage.

Publications

2023

Theodor Westny, Joel Oskarsson, Björn Olofsson, Erik Frisk (2023) MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction With Neural ODEs IEEE Transactions on Intelligent Vehicles, Vol. 8, p. 4223-4236 (Article in journal) Continue to DOI
Joel Oskarsson, Per Sidén, Fredrik Lindsten (2023) Temporal Graph Neural Networks for Irregular Data Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, p. 4515-4531 (Conference paper)
Theodor Westny, Joel Oskarsson, Björn Olofsson, Erik Frisk (2023) Evaluation of Differentially Constrained Motion Models for Graph-Based Trajectory Prediction 2023 IEEE INTELLIGENT VEHICLES SYMPOSIUM, IV (Conference paper) Continue to DOI
Theodor Westny, Joel Oskarsson, Björn Olofsson, Erik Frisk (2023) MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs

2022

Joel Oskarsson, Per Sidén, Fredrik Lindsten (2022) Scalable Deep Gaussian Markov Random Fields for General Graphs Proceedings of the 39th International Conference on Machine Learning, p. 17117-17137 (Conference paper)

Research

About the Division

Colleagues at STIMA

About the Department