Committee and winners for the IOP award at AIM24. From left to right: Susan Cox, Wylie Ahmed, Celia Rowland (IOP), Harshith Bachimanchi, Blanca Zufiria Gerboles, Mirja Granfors, Carlotta Viana, Gajendra Pratap Singh, Giorgio Volpe. (Photo by G. Volpe)Mirja Granfors won the best early career researcher presentation award at AIM 2024 meeting (Artificial Intelligence for iMaging 2024) held in La Ràpita, Spain, from 26 May – 1 June 2024.
The award, consisting of a certificate, and a cash prize of 250 €, is sponsored by Nanophotonics.
Mirja was awarded the prize for her presentation titled “Global graph features unveiled by unsupervised geometric deep learning”. In her presentation, she introduced a novel graph autoencoder designed to capture complex relationships modelled by graphs. She demonstrated the performance of the network across a spectrum of datasets, 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.
Award Certificate. (Image by M. Granfors)
Mirja presents at AIM24 Conference. (Photo by N. C. Palmero Crúz)
The plot shows the latent space of the graph autoencoder. Each point represents a graph, and is coloured based on a structural parameter of the graph. (Image by M. Granfors.)Mirja Granfors defended her Master thesis in physics at the University of Gothenburg on June 8 2023. Congrats!
Title: Enhancing Graph Analysis and Compression with Multihead Attention and Graph-Pooling Autoencoders
Abstract:
Graphs are used to model complex relationships in various domains. Analyzing and classifying graphs efficiently poses significant challenges due to their inherent structural complexity. This thesis presents two distinct projects aimed at enhancing graph analysis and compression through novel and innovative techniques. In the first project, a multihead attention module for node features is developed, enabling effective prediction of graph edges for connection in time. By applying attention mechanisms, the module selectively focuses on relevant features, facilitating accurate edge predictions. This approach expands the potential applications of graph analysis by improving the understanding of graph connectivity and identifying critical relationships between nodes. The second project introduces a novel graph autoencoder with multiple steps of size reduction by graph-pooling. Unlike traditional graph autoencoders, which commonly employ graph convolutional networks, this approach utilizes several poolings to capture diverse structural information and compress the graph representation. The pooling-based autoencoder not only achieves efficient graph compression but also captures the structural information of the graph. This enables the classification of graphs based on their structure, providing a valuable tool for tasks such as graph categorization.
Supervisor: Jesús Pineda Examiner: Giovanni Volpe Opponent: Gideon Jägenstedt
