Networks provide a simple model to understand and predict the emergent behavior of complex systems made of a large number of interacting nonlinear dynamical units. Some of the most challenging and useful problems in network science focus on how structural properties of the underlying interaction network govern the collective dynamical behavior on the network, and how these rules can be discovered from real-world data. The rapid advancement of new machine learning techniques has led to the development of new algorithms and strategies for inference of underlying network structures in datasets, prediction of behavior of complex and dynamical networks, and identification and control of such networks.
In this second installment of the satellite, we are covering topics like machine-learning-based network inference problems, analysis of social networking and human behavior data, and prediction of behavior of complex systems. Social data analysis has emerged as an important topic in the recent years because we have seen a rapid growth of online polarization, and also because new data has been available for human social interactions. Using machine learning for dynamical systems has become important in fields like global climate prediction, and relevant for accelerating state-of-the-art simulations of complex systems.
This satellite meeting aims to bring together the network scientists having expertise in traditional approaches and expert machine learning scientists for exchange of ideas, and formation of a platform for future collaboration, as well as to deliberate upon open problems in the network science which can be addressed by machine learning techniques.
More at: sites.google.com