Master internship

• Get familiar with an already developed federated learning framework that includes the privacy-preserving Source-Free Domain Adaptation (SFDA) approach
• Study the effect of class imbalance on performance in federated learning
• Investigate methods used in supervised domain adaptation and federated learning to address class imbalance
• Propose new strategies based on the insights from the previous objectives

• Currently enrolled in a Master’s degree or engineering program in applied mathematics or computer science
• Solid background in machine learning
• Comfortable with software development, particularly in Python
• Good level of English is strongly recommended

No prior experience in domain adaptation or federated learning is required