On RKHS Choices for Assessing Graph Generators via Kernel Stein Statistics

1 code implementation • 11 Oct 2022 • Moritz Weckbecker, Wenkai Xu, Gesine Reinert

Score-based kernelised Stein discrepancy (KSD) tests have emerged as a powerful tool for the goodness of fit tests, especially in high dimensions; however, the test performance may depend on the choice of kernels in an underlying reproducing kernel Hilbert space (RKHS).

Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence

no code implementations • 7 Feb 2022 • Frederik Pahde, Maximilian Dreyer, Leander Weber, Moritz Weckbecker, Christopher J. Anders, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin

With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space.

TAG