Master's thesis; Causal AI for 5G/6G networks

We have an open position for a master student to join us at the Connected Intelligence research unit, within the Computer Science department at RISE.

Background
In 5G telecom networks, models are often trained in one environment (one cell, one environment, one traffic mix) and then deployed in another with different infrastructure, deployment environment, mobility, and user behavior. These shifts can degrade the performance of ML models, because what looked predictive in one deployment may not hold in another. Collecting new labeled data for every configuration, or scenario is also slow and expensive. Domain generalization aims to build models that keep working under these shifts without retraining, which is critical if operators want stable performance across deployments. A growing direction of research here is causal AI. The goal is to learn relationships that reflect underlying causes, which are more likely to stay consistent across domains with the aim of learning more robust predictors for next generation 6G networks.

Description
This thesis focuses on benchmarking domain shifts in 5G networks. You will generate domain-shifted datasets using simulated networks, then evaluate state-of-the-art causal AI based domain generalization methods under different shift conditions. Finally, you will assess which classes of approaches are most applicable under which types of shifts.

Expected skills

• Programming skills in Python and C++

• Experience in setting up ML models

• Basic knowledge of wireless/telecom networks

Terms

• Start time: as soon as possible

• Scope: 30 hp (20 weeks)

• Location: RISE, Stockholm (Kista). Options to partially work remotely

• Compensation: In line with RISE guidelines we offer 40,000 SEK for a completed thesis of high quality

Welcome with your application!
To know more, please contact Akhila Rao (akhila.rao@ri.se). Applications should include a CV, recent grades, and a code example if possible. Candidates are encouraged to send in their application as soon as possible but at the latest by the 5th of December 2025. Suitable applicants will be interviewed as soon as applications are received.