Deutsch Intern
    Machine Learning for Complex Networks


    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.


    What is the Markov order of paths in a network? In our latest published work, which has been accepted for publication at The Web Conference (WWW'22), we use Bayesian inference and model selection to address this important question in the modelling of time series data on networks.