no code implementations • 28 Nov 2023 • Daqian Shao, Lukas Fesser, Marta Kwiatkowska
Robustness certification, which aims to formally certify the predictions of neural networks against adversarial inputs, has become an integral part of important tool for safety-critical applications.
1 code implementation • 24 Nov 2023 • Lukas Fesser, Melanie Weber
We further show that combining local structural encodings, such as LCP, with global positional encodings improves downstream performance, suggesting that they capture complementary geometric information.
1 code implementation • 17 Sep 2023 • Lukas Fesser, Melanie Weber
Several rewiring approaches utilizing graph characteristics, such as curvature or the spectrum of the graph Laplacian, have been proposed.
1 code implementation • 15 Jun 2023 • Lukas Fesser, Luca D'Amico-Wong, Richard Qiu
Physics-informed Neural Networks (PINNs) have recently gained popularity due to their effective approximation of partial differential equations (PDEs) using deep neural networks (DNNs).