Mirja Granfors, Jesús Pineda, Blanca Zufiria Gerbolés, Jiawei Sun, Joana B. Pereira, Carlo Manzo, and Giovanni Volpe
Date: 19 August 2024
Time: 17:30-19:00 (PDT)
Graphs are used to model complex relationships in various domains, such as interacting particles or neural connections within a brain. Efficient analysis and classification of graphs pose significant challenges due to their inherent structural complexity and variability. Here, an approach is presented to address these challenges through the development of the graph autoencoder GAUDI. GAUDI effectively summarizes graph structures while preserving important topological details through multiple hierarchical pooling steps. This enables the extraction of physical parameters describing the graphs. We demonstrate the performance of GAUDI across diverse graph data originating from complicated systems, including the classification of protein assembly structures from single-molecule localization microscopy data, as well as the analysis of collective behavior and correlations between brain connections and age. This approach holds great promise for examining diverse systems, enhancing our comprehension of various forms of graph data.