Skip to content

Highlights

Selected results of the lab, newest first. Each highlight connects a research question with selected papers, code and data.

  1. A noisy random graph branches into two generated graphs: a sparse spatial graph beside a transmission tower, for infrastructure and transport networks, and a modular graph beside a howling wolf, for social networks.

    Learning on Graphs

    What a generated graph should preserve

    How can generated graphs preserve the structures that distinguish real network domains, and how can generation be steered towards a target class?

  2. A painted brain with sampled areas joined by grey candidate links. Dashed leaders connect five areas to activity traces; the three traces that share one rhythm turn blue, and a blue sub-network appears over washed brain areas.

    Learning on Graphs

    From brain signals to meaningful networks

    How can brain activity recordings reveal the interactions that distinguish subjects and characterise brain disorders?

  3. Illustrative food web in which a daisy wilts and its two feeding links become dashed red lines. Blue links from a healthy aster show that the bee and aphid retain another resource; other feeding links are shown in blue-gray.
  4. World wheat-trade network under a simulated US production shock. A wheat illustration wilts; dashed red arrows then show reduced flows spreading from the United States, and blue arrows show approximately conserved flows. Red country fills highlight the shock origin and selected recipients with reduced imports against a sage geographic background.