Deutsch Intern
Machine Learning for Complex Networks

Archiv

In our new paper Modeling Social Resilience: Questions, Answers, Open Problems, which was recently published in Advances in Complex Systems, we present a modelling framework that captures two dimensions of resilience: robustness and adaptivity.

more

We have just released a new preprint on De Bruijn Graph Neural Networks, a new approach to time-aware graph learning that leverages the causal topology of time-stamped network data.

more

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).

more

Today, Prof. Ingo Scholtes will give a lecture on higher-order graph models at the Summer School on Mathematics of Complex Social Systems, which is held at the Berlin Mathematics Research Center Math+, Germany.

more

We are happy to learn that our poster submission Willing to revise? Confidence and Recommendation Adoption in AI-Assisted Image Recognition has been accepted at the International Conference on Hybrid Human-Artificial Intelligence in Amsterdam, Netherlands.

more

On January 14th, Prof. Dr. Ingo Scholtes will give a talk in the AI Talks @ JMU series. The talk with the title "What makes teams successful? Insights from Repository Mining, Network Science, and Empirical Software Engineering" addresses the question how we can use massive data on software repositories to gain insights into collaborative software engineering.

more

The final report of our Dagstuhl Seminar on "Higher-Order Graph Models: From Theoretical Foundations to Machine Learning" has now been published in the series Dagstuhl Reports of the Leibniz Zentrum für Informatik.

more

In our recent preprint "Sequential Motifs in Observed Walks" we use higher-order graph models for causal paths to analyze patterns in time series data on networks. The study has been led by collaborators at Northeastern University in Boston, USA.

more

Given the observation of a dynamical process in an an unobserved networked system, what can we say about the underlying interaction topology? Our latest study led by Dr. Unai Alvarez-Rodriguez addresses this important question.

more

We are happy to announce that our latest study "Big Data = Big Insights? Operationalizing Brooks’ Law in a Massive GitHub Data Set" was accepted for the technical track of the 44th International Conference on Software Engineering (ICSE), to be held in May 2022 in Philadelphia, PA, USA.

more