SPS DSI (DEGAS) Webinar: 18 January 2023, presented by Dr. Stephan Günnemann

Upcoming IEEE SPS-DSI (DEGAS) Webinar
IEEE Data Science Initiative Webinar

Title: Robustness of Graph Neural Networks
Date: 18 January 2023
Time: 3:00 PM (Paris time) | (Local time zone)
Duration: Approximately 1 hour
Speaker: Dr. Stephan Günnemann

Register for the Webinar

The DEGAS Webinar Series is an event initiated by the Data Science Initiative (DSI) of the IEEE Signal Processing (SP) Society. The goal is to provide the SP community with updates and advances in learning and inference on graphs. Signal processing and machine learning often deal with data living in regular domains such as space and time. This webinar series will cover the extension of these methods to network data, including topics such as graph filtering, graph sampling, spectral analysis of network data, graph topology identification, geometric deep learning, and so on. Applications can for instance be found in image processing, social networks, epidemics, wireless communications, brain science, recommender systems, and sensor networks. These bi-weekly webinars will be hosted on Zoom, with recordings made available in the IEEE Signal Processing Society’s  YouTube channel following the live events. Further details about live and streaming access will follow.

Abstract:

Speaker Biography:

Stephan Günnemann received the doctoral degree at RWTH Aachen University, Germany, in the field of computer science.

From 2012 to 2015, he was an associate of Carnegie Mellon University, Pittsburgh, PA, USA. Currently, he is a Professor at the Department of Computer Science, Technical University of Munich and Executive Director of the Munich Data Science Institute. His main research focuses on reliable machine learning for graphs and temporal data. He is particularly interested in graph neural networks (GNNs) and their application for, e.g., molecular modeling.

Prof. Günnemann has received a Google Faculty Research Award and is a Junior-Fellow of the German Computer Science Society. His works on subspace clustering on graphs as well as adversarial robustness of GNNs have received the best research paper awards at ECML-PKDD and KDD.