Klaus-Robert Müller — accepted AI-conference papers

2023

Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations

Alexander Binder, Leander Weber, Sebastian Lapuschkin, Grégoire Montavon, Klaus-Robert Müller, Wojciech Samek

CVPR 2023poster

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. Specifically model randomization testing can be overinterpreted if regarded as a primary criterion for selecting or discarding exp…

Cited by 27 Source ↗PDF ↗Scholar ↗

2022

Efficient Computation of Higher-Order Subgraph Attribution via Message Passing

Ping Xiong, Thomas Schnake, Grégoire Montavon, Klaus-Robert Müller, Shinichi Nakajima

ICML 2022spotlight

Explaining graph neural networks (GNNs) has become more and more important recently. Higher-order interpretation schemes, such as GNN-LRP (layer-wise relevance propagation for GNN), emerged as powerful tools for unraveling how different features interact thereby contributing to explaining GNNs. GNN-…

Cited by 12 Source ↗PDF ↗code ↗Scholar ↗

2022

XAI for Transformers: Better Explanations through Conservative Propagation

Ameen Ali, Thomas Schnake, Oliver Eberle, Grégoire Montavon, Klaus-Robert Müller, Lior Wolf

ICML 2022spotlight

Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on gradient information, have been proposed. We show that the gradi…

Cited by 128 Source ↗PDF ↗code ↗Scholar ↗

2020

Deep Semi-Supervised Anomaly Detection

Lukas Ruff, Robert A. Vandermeulen, Nico Görnitz, Alexander Binder, Emmanuel Müller, Klaus-Robert Müller +1

ICLR 2020poster

Deep approaches to anomaly detection have recently shown promising results over shallow methods on large and complex datasets. Typically anomaly detection is treated as an unsupervised learning problem. In practice however, one may have---in addition to a large set of unlabeled samples---access to a…

Cited by 824 Source ↗code ↗Scholar ↗

2020

Fairwashing explanations with off-manifold detergent

Christopher Anders, Plamen Pasliev, Ann-Kathrin Dombrowski, Klaus-Robert Müller, Pan Kessel

ICML 2020poster

Explanation methods promise to make black-box classifiers more transparent. As a result, it is hoped that they can act as proof for a sensible, fair and trustworthy decision-making process of the algorithm and thereby increase its acceptance by the end-users. In this paper, we show both theoreticall…

Cited by 109 Source ↗PDF ↗code ↗Scholar ↗

2020

On the Byzantine Robustness of Clustered Federated Learning

Felix Sattler, Klaus-Robert Müller, Thomas Wiegand, Wojciech Samek

ICASSP 2020accepted

Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularity, it has been observed that Federated Learning yields suboptimal results if the local clients' data distributions diver…

Cited by 0 Source ↗Scholar ↗

2019

Explanations can be manipulated and geometry is to blame

Ann-Kathrin Dombrowski, Maximillian Alber, Christopher Anders, Marcel Ackermann, Klaus-Robert Müller, Pan Kessel

NeurIPS 2019poster

Explanation methods aim to make neural networks more trustworthy and interpretable. In this paper, we demonstrate a property of explanation methods which is disconcerting for both of these purposes. Namely, we show that explanations can be manipulated arbitrarily by applying visually hardly percepti…

Cited by 423 Source ↗PDF ↗code ↗Scholar ↗

2019

Partial Optimality of Dual Decomposition for MAP Inference in Pairwise MRFs

Alexander Bauer, Shinichi Nakajima, Nico Goernitz, Klaus-Robert Müller

AISTATS 2019poster

Markov random fields (MRFs) are a powerful tool for modelling statistical dependencies for a set of random variables using a graphical representation. An important computational problem related to MRFs, called maximum a posteriori (MAP) inference, is finding a joint variable assignment with the maxi…

Cited by 7 Source ↗PDF ↗Scholar ↗

2018

How are the Centered Kernel Principal Components Relevant to Regression Task? -An Exact Analysis

Masahiro Yukawa, Klaus-Robert Müller, Yuto Ogino

ICASSP 2018accepted

We present an exact analytic expression of the contributions of the kernel principal components to the relevant information in a nonlinear regression problem. A related study has been presented by Braun, Buhmann, and Müller in 2008, where an upper bound of the contributions was given for a general s…

Cited by 0 Source ↗Scholar ↗

2018

Learning how to explain neural networks: PatternNet and PatternAttribution

Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, Klaus-Robert Müller, Dumitru Erhan, Been Kim +1

ICLR 2018poster

DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. Yet they are used on multi-layer networks with millions of parameters. This is a cause for concern since linea…

Cited by 433 Source ↗PDF ↗Scholar ↗

2017

An Empirical Study on The Properties of Random Bases for Kernel Methods

Maximilian Alber, Pieter-Jan Kindermans, Kristof Schütt, Klaus-Robert Müller, Fei Sha

NeurIPS 2017poster

Kernel machines as well as neural networks possess universal function approximation properties. Nevertheless in practice their ways of choosing the appropriate function class differ. Specifically neural networks learn a representation by adapting their basis functions to the data and the task at han…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2017

Interpretable human action recognition in compressed domain

Vignesh Srinivasan, Sebastian Lapuschkin, Cornelius Hellge, Klaus-Robert Müller, Wojciech Samek

ICASSP 2017accepted

Compressed domain human action recognition algorithms are extremely efficient, because they only require a partial decoding of the video bit stream. However, the question what exactly makes these algorithms decide for a particular action is still a mystery. In this paper, we present a general method…

Cited by 0 Source ↗Scholar ↗

2017

Minimizing Trust Leaks for Robust Sybil Detection

János Höner, Shinichi Nakajima, Alexander Bauer, Klaus-Robert Müller, Nico Görnitz

ICML 2017poster

Sybil detection is a crucial task to protect online social networks (OSNs) against intruders who try to manipulate automatic services provided by OSNs to their customers. In this paper, we first discuss the robustness of graph-based Sybil detectors SybilRank and Integro and refine theoretically thei…

Cited by 18 Source ↗PDF ↗Scholar ↗

2017

SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

Kristof Schütt, Pieter-Jan Kindermans, Huziel Enoc Sauceda Felix, Stefan Chmiela, Alexandre Tkatchenko, Klaus-Robert Müller

NeurIPS 2017poster

Deep learning has the potential to revolutionize quantum chemistry as it is ideally suited to learn representations for structured data and speed up the exploration of chemical space. While convolutional neural networks have proven to be the first choice for images, audio and video data, the atoms i…

Cited by 1597 Source ↗PDF ↗Scholar ↗

2016

Wasserstein Training of Restricted Boltzmann Machines

Grégoire Montavon, Klaus-Robert Müller, Marco Cuturi

NeurIPS 2016poster

Boltzmann machines are able to learn highly complex, multimodal, structured and multiscale real-world data distributions. Parameters of the model are usually learned by minimizing the Kullback-Leibler (KL) divergence from training samples to the learned model. We propose in this work a novel approac…

Cited by 150 Source ↗PDF ↗Scholar ↗