2.8k citations · 9.6k across the 55 of their papers we have counts for
58 papers
Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structures
Ping Xiong, Thomas Schnake, Grégoire Montavon +2
To understand how a neural network (NN) functions and makes predictions, it has become increasingly clear that analyzing only the input domain is insufficient -- one must also exam…
Conveyance: A Versatile Framework for Learning in Structured Class Spaces
Yasser Taha, Grégoire Montavon, Nils Körber
While machine learning (ML) architectures have evolved rapidly to account for complex data, loss functions like cross-entropy remain mostly structure-agnostic in many real-world ap…
Relevant Walk Search for Explaining Graph Neural Networks
Ping Xiong, Thomas Schnake, Michael Gastegger +3
Graph Neural Networks (GNNs) have become important machine learning tools for graph analysis, and its explainability is crucial for safety, fairness, and robustness. Layer-wise rel…
Investigating the Robustness of Subtask Distillation under Spurious Correlation
Pattarawat Chormai, Klaus-Robert Müller, Grégoire Montavon
Subtask distillation is an emerging paradigm in which compact, specialized models are extracted from large, general-purpose 'foundation models' for deployment in environments with…
Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces
Pattarawat Chormai, Ali Hashemi, Klaus-Robert Müller +1
Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environment…
Drainage: A Unifying Framework for Addressing Class Uncertainty
Yasser Taha, Grégoire Montavon, Nils Körber
Modern deep learning faces significant challenges with noisy labels, class ambiguity, as well as the need to robustly reject out-of-distribution or corrupted samples. In this work,…
Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples
Sidney Bender, Ole Delzer, Jan Herrmann +3
Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-super…
Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
Florian Bley, Jacob Kauffmann, Simon León Krug +2
Distance-based classifiers, such as k-nearest neighbors and support vector machines, continue to be a workhorse of machine learning, widely used in science and industry. In practic…
MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification
David Jacob Drexlin, Jonas Dippel, Julius Hense +4
Deep learning models have made significant advances in histological prediction tasks in recent years. However, for adaptation in clinical practice, their lack of robustness to vary…
Towards Desiderata-Driven Design of Visual Counterfactual Explainers
Sidney Bender, Jan Herrmann, Klaus-Robert Müller +1
Visual counterfactual explainers (VCEs) are a straightforward and promising approach to enhancing the transparency of image classifiers. VCEs complement other types of explanations…
Wasserstein Distances Made Explainable: Insights Into Dataset Shifts and Transport Phenomena
Philip Naumann, Jacob Kauffmann, Grégoire Montavon
Wasserstein distances provide a powerful framework for comparing data distributions. They can be used to analyze processes over time or to detect inhomogeneities within data. Howev…
Uncovering the Structure of Explanation Quality with Spectral Analysis
Johannes Maeß, Grégoire Montavon, Shinichi Nakajima +2
As machine learning models are increasingly considered for high-stakes domains, effective explanation methods are crucial to ensure that their prediction strategies are transparent…
Opportunities and limitations of explaining quantum machine learning
Elies Gil-Fuster, Jonas R. Naujoks, Grégoire Montavon +3
A common trait of many machine learning models is that it is often difficult to understand and explain what caused the model to produce the given output. While the explainability o…
Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
Malte Esders, Thomas Schnake, Jonas Lederer +4
While machine learning (ML) models have been able to achieve unprecedented accuracies across various prediction tasks in quantum chemistry, it is now apparent that accuracy on a te…
Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
Thomas Schnake, Farnoush Rezaei Jafari, Jonas Lederer +5
Explainable Artificial Intelligence (XAI) plays a crucial role in fostering transparency and trust in AI systems, where traditional XAI approaches typically offer one level of abst…
The Clever Hans Effect in Unsupervised Learning
Jacob Kauffmann, Jonas Dippel, Lukas Ruff +3
Unsupervised learning has become an essential building block of AI systems. The representations it produces, e.g. in foundation models, are critical to a wide variety of downstream…
MambaLRP: Explaining Selective State Space Sequence Models
Farnoush Rezaei Jafari, Grégoire Montavon, Klaus-Robert Müller +1
Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing…
XpertAI: uncovering regression model strategies for sub-manifolds
Simon Letzgus, Klaus-Robert Müller, Grégoire Montavon
In recent years, Explainable AI (XAI) methods have facilitated profound validation and knowledge extraction from ML models. While extensively studied for classification, few XAI so…
Explaining Predictive Uncertainty by Exposing Second-Order Effects
Florian Bley, Sebastian Lapuschkin, Wojciech Samek +1
Explainable AI has brought transparency into complex ML blackboxes, enabling, in particular, to identify which features these models use for their predictions. So far, the question…
Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI
Oliver Eberle, Jochen Büttner, Hassan El-Hajj +3
Historical materials are abundant. Yet, piecing together how human knowledge has evolved and spread both diachronically and synchronically remains a challenge that can so far only…
Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation
Sidney Bender, Christopher J. Anders, Pattarawatt Chormai +3
This paper introduces a novel technique called counterfactual knowledge distillation (CFKD) to detect and remove reliance on confounders in deep learning models with the help of hu…
Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
Lorenz Linhardt, Klaus-Robert Müller, Grégoire Montavon
Robustness has become an important consideration in deep learning. With the help of explainable AI, mismatches between an explained model's decision strategy and the user's domain…
Explainable AI for Time Series via Virtual Inspection Layers
Johanna Vielhaben, Sebastian Lapuschkin, Grégoire Montavon +1
The field of eXplainable Artificial Intelligence (XAI) has greatly advanced in recent years, but progress has mainly been made in computer vision and natural language processing. F…
Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
Pattarawat Chormai, Jan Herrmann, Klaus-Robert Müller +1
Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. Explanations often take the form of…