On July 10, 2026, an open lecture was held in hall 113 of the CoE UNITe by Assoc. Prof. Elena Zheleva of the University of Illinois at Chicago, a visiting researcher at UNITe this month.
The lecture “Causal Inference from Network Data” provided an overview of the main concepts in causal inference and the challenges involved in studying real-world systems with relational and network structures. New methods for identifying causal relationships and approaches for assessing the heterogeneous effects of interventions in networks were examined, which make it possible to identify the individuals and communities that benefit most from a specific intervention. The research presented expands the capabilities of causal analysis in complex, interconnected systems and contributes to the development of AI systems capable of understanding not only correlations but also causal relationships.
Causal inference examines how various interventions affect outcomes. Unlike traditional machine learning, which focuses on prediction, it evaluates the effects of actions, policies, and interventions, thereby supporting informed decision-making. This approach is of key importance for public health, social media, recommendation systems, and scientific research, and with the development of artificial intelligence, it is becoming the foundation for building reliable, explainable, and fair AI systems.
