COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |

University of Cambridge > Talks.cam > Cambridge Image Analysis Seminars > Graph Neural Networks Use Graphs When They Shouldn’t

## Graph Neural Networks Use Graphs When They Shouldn’tAdd to your list(s) Download to your calendar using vCal - Maya Bechler-Speicher, Tel Aviv University
- Friday 01 November 2024, 14:00-15:00
- MR2 Centre for Mathematical Sciences.
If you have a question about this talk, please contact Ferdia Sherry. Predictions over graphs play a crucial role in various domains, including social networks and medicine. Graph Neural Networks (GNNs) have emerged as the dominant approach for learning on graph data. Although a graph-structure is provided as input to the GNN , in some cases the best solution can be obtained by ignoring it. While GNNs have the ability to ignore the graph-structure in such cases, it is not clear that they will. In this talk, I will show that GNNs actually tend to overfit the given graph-structure. Namely, they use it even when a better solution can be obtained by ignoring it. By analyzing the implicit bias of gradient-descent learning of GNNs I will show that when the ground truth function does not use the graphs, GNNs are not guaranteed to learn a solution that ignores the graph, even with infinite data. I will prove that within the family of regular graphs, GNNs are guaranteed to extrapolate when learning with gradient descent. Then, based on our empirical and theoretical findings, I will demonstrate on real-data how regular graphs can be leveraged to reduce graph overfitting and enhance performance. Finally, I will present a recent novel approach, Cayley Graph Propagation, for propagating information over special types of regular graphs – the Cayley graphs of the SL(2, Zn) special linear group, to improve overfitting and information bottlenecks. This talk is part of the Cambridge Image Analysis Seminars series. ## This talk is included in these lists:Note that ex-directory lists are not shown. |
## Other listsCambridge ESRC DTP Annual Lecture Zoology Postdoc Summer Seminar Series Optoelectronics Group## Other talksVisual Digital Twins of Forests Quantum Groups Neural Network Verification as a Programming Language Challenge On the bright side: new developments in Marine Cloud Brightening technology Mini Course - Random interlacements and the Gaussian free field |