897 citations · 1.5k across the 18 of their papers we have counts for
19 papers
Towards Fast and Disentangled Counterfactuals for Visual Foundation Models
Sidney Bender, Benedikt Kunz, Ahmed Zeid +3
Foundation models remain vulnerable to spurious correlations and ``Clever Hans'' strategies. Explainable machine learning can find and remove such strategies for classifiers withou…
Set Learning for Accurate and Calibrated Models
Lukas Muttenthaler, Robert A. Vandermeulen, Qiuyi Zhang +2
Model overconfidence and poor calibration are common in machine learning and difficult to account for when applying standard empirical risk minimization. In this work, we propose a…
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
Alexander Binder, Leander Weber, Sebastian Lapuschkin +3
While the evaluation of explanations is an important step towards trustworthy models, it needs to be done carefully, and the employed metrics need to be well-understood. Specifical…
Self-Supervised Training with Autoencoders for Visual Anomaly Detection
Alexander Bauer, Shinichi Nakajima, Klaus-Robert Müller
We focus on a specific use case in anomaly detection where the distribution of normal samples is supported by a lower-dimensional manifold. Here, regularized autoencoders provide a…
Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations
Oliver T. Unke, Martin Stöhr, Stefan Ganscha +8
Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes. Accurate MD simulations require computationally demanding quantum-mechanical ca…
Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images
Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen +3
Due to the intractability of characterizing everything that looks unlike the normal data, anomaly detection (AD) is traditionally treated as an unsupervised problem utilizing only…
Efficient Hierarchical Bayesian Inference for Spatio-temporal Regression Models in Neuroimaging
Ali Hashemi, Yijing Gao, Chang Cai +4
Several problems in neuroimaging and beyond require inference on the parameters of multi-task sparse hierarchical regression models. Examples include M/EEG inverse problems, neural…
On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy
Vignesh Srinivasan, Nils Strodthoff, Jackie Ma +3
There is an increasing number of medical use-cases where classification algorithms based on deep neural networks reach performance levels that are competitive with human medical ex…
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…
A Unifying Review of Deep and Shallow Anomaly Detection
Lukas Ruff, Jacob R. Kauffmann, Robert A. Vandermeulen +5
Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text.…
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…
Explainable Deep One-Class Classification
Philipp Liznerski, Lukas Ruff, Robert A. Vandermeulen +3
Deep one-class classification variants for anomaly detection learn a mapping that concentrates nominal samples in feature space causing anomalies to be mapped away. Because this tr…
The Clever Hans Effect in Anomaly Detection
Jacob Kauffmann, Lukas Ruff, Grégoire Montavon +1
The 'Clever Hans' effect occurs when the learned model produces correct predictions based on the 'wrong' features. This effect which undermines the generalization capability of an…
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…
Rethinking Assumptions in Deep Anomaly Detection
Lukas Ruff, Robert A. Vandermeulen, Billy Joe Franks +2
Though anomaly detection (AD) can be viewed as a classification problem (nominal vs. anomalous) it is usually treated in an unsupervised manner since one typically does not have ac…
Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
Huziel E. Sauceda, Stefan Chmiela, Igor Poltavsky +2
Highly accurate force fields are a mandatory requirement to generate predictive simulations. Here we present the path for the construction of machine learned molecular force fields…
Efficient prediction of 3D electron densities using machine learning
Mihail Bogojeski, Felix Brockherde, Leslie Vogt-Maranto +4
The Kohn-Sham scheme of density functional theory is one of the most widely used methods to solve electronic structure problems for a vast variety of atomistic systems across diffe…
Validity of time reversal for testing Granger causality
Irene Winkler, Danny Panknin, Daniel Bartz +2
Inferring causal interactions from observed data is a challenging problem, especially in the presence of measurement noise. To alleviate the problem of spurious causality, Haufe et…