New preprint

The paper “Interpreting Temporal Graph Neural Networks with Koopman Theory” by Michele Guerra, Simone Scardapane, and Filippo Maria Bianchi is out!

The paper proposes a XAI technique based on Koopman theory to interpret temporal graphs and spatio-temporal GNNs. The proposed approach allows to identify nodes and time steps when relevant events occur.

The preprint is available on Arxiv and the code on Github.