PhD
Chair of Data Analytics and Machine Learning at TUM
Informatik 26
Department of Computer Science
Boltzmannstr. 3
85748 Garching
Biosketch
Amine is a PhD student at the Technical University of Munich working with Prof. Stephan Günnemann. He is broadly interested in the foundations of AI and machine learning and their real-world applications. His current research aims to develop reliable generative models for complex domains, ranging from biological systems to interlinked business data. Amine holds a Bachelor’s degree in Electrical Engineering and a Master’s degree in Robotics & AI. He has been part of the relAI family since 2022.
relAI Research
Deep Generative Models for Complex Data Domains
In my research, I am interested in the foundations of deep generative models, especially diffusion- and flow-based models, as well as their adaptation to complex data domains such as graphs, point clouds, and time series. Recently, I developed a method that maps discrete graphs into a continuous Euclidean space and learns a continuous diffusion model in that space, outperforming discrete graph diffusion models and unlocking a wide range of applications. Currently, I am working on developing generative models for large relational databases by leveraging graph and tabular diffusion models to generate synthetic data that protects the privacy of the real data while capturing its statistical properties, which can then be used as a drop-in replacement for real data in privacy-sensitive applications. More broadly, I am also studying the limitations of current models, such as their slow sampling speed and limited generalization capabilities and thinking about ways to address them.