[Statlist] Research Seminar in Statistics *FRIDAY, 21 OCTOBER 2022* GSEM, University of Geneva

gsem-support-instituts g@em-@upport-|n@t|tut@ @end|ng |rom un|ge@ch
Mon Oct 17 10:49:00 CEST 2022


Dear All,

We are pleased to invite you to our next Research Seminar.

Looking forward to seeing you,


Organized by Professor Sebastian Engelke on behalf of the Research Center for Statistics (https://www.unige.ch/gsem/en/research/institutes/rcs/)


FRIDAY, 21 OCTOBER 2022 at 11:15am, Uni-Mail M 5220 & ONLINE
Zoom research webinar: https://unige.zoom.us/j/92924332087?pwd=U1U1NFk4dTFCRHBMeWYrSDBQcXBiQT09
Meeting ID: 929 2433 2087
Passcode: 399192

Graph Signal Processing: Neural Nets and Beyond
Pierre VANDERGHEYNST, EPFL, Switzerland
https://people.epfl.ch/pierre.vandergheynst

ABSTRACT:
Graph Neural Networks (GNNs) have recently had a tremendous impact in Machine Learning across an impressively broad range of applications. Recent results have shown that they also have limitations (oversmoothing, lack of expressivity, ...) that are often tightly linked to the underlying graph on which they are built.

In this talk we will review the construction of graph neural networks from a graph signal processing perspective and highlight some of these limitations as well as some of the solutions proposed as remedy. We will then leverage this to construct a novel feature convolutional layer that seeks to decouple the structural and computational role of the graph.


Visit the website: https://www.unige.ch/gsem/en/research/seminars/rcs/



More information about the Statlist mailing list