Explainable AI and Interpretability: Research focusing on the explainability of AI models, offering local explanations for predictions, algorithmic recourse, and user-guided explainability.
Ethics and Fairness in AI: Studies discussing ethical implications of AI, with emphasis on balancing actionable explanations and the right to be forgotten, and ensuring fairness in accordance with European values.
Performance Evaluation, Efficiency, and Accountability of AI Models: Research discussing efficient strategies for evaluating and auditing AI models, especially those for evolving data streams, attribution methods, and data recovered from embedding spaces (through generative approaches).
AI for Challenging Datasets and their Combination, e.g., Tabular Data, Streaming Data, Text Data, Image Data
Deep Learning with Tabular Data and Text Data: Work on the use of deep neural networks for analyzing tabular data and methods for generating realistic tabular data with language models.
AI for Data Streams: Research focusing on the detection of change in evolving data streams and the development of interpretable models for data streams.
Concept Discovery for Explainable AI for Image Data: Research on the reliable detection of unique concepts (e.g., colour, shape, object type, ...) that occur in images for better explanations.
Responsible and Effective Application of AI
AI in Finance: Research on reliable and explainable AI solutions for financial services (identity protection, fraud prevention, risk prediction, link prediction, data completion, and many more).
AI in Education: Research investigating opportunities and challenges of applying AI, particularly large language models, in education.
AI in Healthcare: Studies focusing on applications of AI in healthcare, particularly in medical imaging.