J2 - TG-DGM: Clustering Brain Activity using a Temporal Graph Deep Generative Model
Simeon Emilov Spasov, Alexander Campbell, Giovana Dimitri, Alessandro Di Stefano, franco scarselli, Pietro Lio
Spatiotemporal graphs are a natural representation of dynamic brain activity derived from functional magnetic imaging (fMRI) data. Previous works, however, tend to ignore time dynamics of the brain and focus on static graphs. In this paper, we propose a temporal graph deep generative model (TG-DGM) which clusters brain regions into communities that evolve over time. In particular, subject embeddings capture inter-subject variability and its impact on communities using neural networks. We validate our model on the UK Biobank data. Results of up to 0.81 AUC ROC on the task of biological sex classification demonstrate that injecting time dynamics in our model outperforms a static baseline.
Friday 9th July
J1-9 (short): Unsupervised and Representation Learning - 13:45 - 14:30 (UTC+2)