Berlin 2024 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

SOE: Fachverband Physik sozio-ökonomischer Systeme

SOE 2: Focus Session: Machine Learning for Complex Socio-economic Systems

Montag, 18. März 2024, 09:30–12:00, MA 001

The intersection of physics and machine learning presents a promising avenue for investigating the structure and dynamics of complex socio-economic systems, e.g., by processing vast and diverse datasets. By incorporating physics-based insights and approaches into machine learning algorithms, a more comprehensive understanding of the underlying mechanisms that drive economic and social phenomena can be achieved, paving the way for more informed policy decisions, risk assessments, and the identification of emergent patterns critical for navigating the complexities of modern societies.
With this focus session, we aim to highlight recent results and discuss trends in this interdisciplinary field.

Organized by Ingo Scholtes (Universität Würzburg, Germany) and Philipp Hövel (Saarland University, Germany)

	09:30	SOE 2.1	Hauptvortrag: Collective emotions and polarization on social media — •Kristina Lerman
	10:00	SOE 2.2	Collaboration, not polarization: A Relational Graph Convolutional Network (RGCN) model to disentangle active and passive cosponsorship in the U.S. Congress — •Frank Schweitzer
	10:15	SOE 2.3	Inferring the Utility from Optimal Behaviour in an Epidemic using Neural Networks — •Mark Lynch, Matthew Turner, John Molina, Simon Schnyder, and Ryoichi Yamamoto
	10:30	SOE 2.4	Topical Talk: Prediction of processes on networks — •Piet Van Mieghem
	10:50		10 min. break
	11:00	SOE 2.5	Towards a complex systems theory of attention? — •Claudius Gros
	11:15	SOE 2.6	Using Causality-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs — •Franziska Heeg and Ingo Scholtes
	11:30	SOE 2.7	How much do nodes in socioeconomic networks rely on their neighborhood? — •Nimrah Mustafa and Rebekka Burkholz
	11:45	SOE 2.8	The Map Equation Goes Neural — Chester Tan, Christopher Blöcker, and •Ingo Scholtes