Deutsch Intern
Machine Learning for Complex Networks

Paper accepted at IEEE/ACM ASONAM 2022


Our manuscript Predicting Influential Higher-Order Patterns in Temporal Network Data has been accepted for publication at the IEEE/ACM International Conference on Social Networks Analysis and Mining (ASONAM 2022).

In our work, we use a multi-order generative model of paths to define time-aware centralities of nodes, and use them to predict node centralities in out-of-sample data. Our work sheds light on the importance of temporal information for the ranking of nodes in complex networks.