Deep Graph Learning for Temporal Data — I. Scholtes, University of Würzburg | HAICON26

Speaker: I. Scholtes Affiliation: University of Würzburg, Germany Date: June 10, 2026 Time: 12:00–12:15pm (Invited Talk) Session: AI Research across Bavaria (co-organized by BAIOSPHERE) Recorded at the Helmholtz AI Conference (HAICON26), June 9–11, 2026. More info: https://haicon.cc/conference-program/ About this talk: Deep Graph Learning for Temporal Data I. Scholtes 1 1 University of Würzburg, Germany This invited talk introduces challenges in extending deep graph learning to temporal graphs, focusing on the arrow of time and causal topology — which nodes can causally influence each other over time. It presents a causality-aware temporal GNN architecture and recent advances in GNN expressive power for time series on biological, social, and technical systems.