268 citations · 470 across the 19 of their papers we have counts for
8 papers · 1 filter
Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows
Lorenz Vaitl, Kim A. Nicoli, Shinichi Nakajima +1
We propose an algorithm to estimate the path-gradient of both the reverse and forward Kullback-Leibler divergence for an arbitrary manifestly invertible normalizing flow. The resul…
Path-Gradient Estimators for Continuous Normalizing Flows
Lorenz Vaitl, Kim A. Nicoli, Shinichi Nakajima +1
Recent work has established a path-gradient estimator for simple variational Gaussian distributions and has argued that the path-gradient is particularly beneficial in the regime i…
Optimal Sampling Density for Nonparametric Regression
Danny Panknin, Klaus Robert Müller, Shinichi Nakajima
We propose a novel active learning strategy for regression, which is model-agnostic, robust against model mismatch, and interpretable. Assuming that a small number of initial sampl…
Langevin Cooling for Domain Translation
Vignesh Srinivasan, Klaus-Robert Müller, Wojciech Samek +1
Domain translation is the task of finding correspondence between two domains. Several Deep Neural Network (DNN) models, e.g., CycleGAN and cross-lingual language models, have shown…
How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
Kirill Bykov, Marina M. -C. Höhne, Klaus-Robert Müller +2
Explainable AI (XAI) aims to provide interpretations for predictions made by learning machines, such as deep neural networks, in order to make the machines more transparent for the…
Higher-Order Explanations of Graph Neural Networks via Relevant Walks
Thomas Schnake, Oliver Eberle, Jonas Lederer +4
Graph Neural Networks (GNNs) are a popular approach for predicting graph structured data. As GNNs tightly entangle the input graph into the neural network structure, common explain…
Towards Best Practice in Explaining Neural Network Decisions with LRP
Maximilian Kohlbrenner, Alexander Bauer, Shinichi Nakajima +3
Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intranspa…
Robustifying Models Against Adversarial Attacks by Langevin Dynamics
Vignesh Srinivasan, Arturo Marban, Klaus-Robert Müller +2
Adversarial attacks on deep learning models have compromised their performance considerably. As remedies, a lot of defense methods were proposed, which however, have been circumven…