Graph Machine Learning & Graph Neural Networks
Graph representation learning, graph autoencoders, attention-based graph models and learning from relational structure.
Research
Machine learning on structured, complex and real-world data.
My research interests center on representation learning, graph-based methods, unsupervised learning and applied AI.
Unsupervised Anomaly Detection
Representation-based approaches for identifying unusual nodes, patterns and structures without relying on dense supervision.
AI for Healthcare & Time-Series
Machine learning for sensor data, activity monitoring, fall detection and other real-world sequential data settings.
Generative AI & AI in Education
Responsible integration of generative AI, educational applications and evaluation of AI-assisted learning systems.