social networks

For nation-scale networks, we present a layer-sensitive random walk, temporal alignment and partitioning techniques and evaluate them on 13 downstream tasks.

We create network embeddings of the Dutch population, use them to predict voting behavior, and explore interpretability techniques for network embeddings.

We study the role of collaboration networks for placing PhD students in the U.S. We observe a sizable citation premium for graduates placed through the advisor’s network. However, when comparing graduates hired at the same university, the productivity premium is fully explained by public information on the productivity at the time of graduation.