1.6k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Technische Universität BerlinDE42 papers
- Korea UniversityKR18 papers
- Max Planck Institute for InformaticsDE15 papers
- Fraunhofer Institute for Telecommunications, Heinrich Hertz InstituteDE9 papers
- RIKEN Center for Advanced Intelligence ProjectJP6 papers
- Brain (Germany)DE5 papers
- Deutsches Elektronen-Synchrotron DESYDE4 papers
- University of BaselCH4 papers
- Cyprus InstituteCY3 papers
- Freie Universität BerlinDE3 papers
- University of TorontoCA3 papers
- University of ViennaAT3 papers
46 papers
Distributed Sparse Interventions in Language Models
Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1
Language models can perform a wide range of tasks at various levels of abstraction. They flexibly infer tasks from context, execute multiple tasks simultaneously, and select among…
Gradient-Guided Furthest Point Sampling for Robust Training Set Selection
Morris Trestman, Stefan Gugler, Felix A. Faber +1
Training set sampling methods are used to improve model performance and lower data costs in machine learning problems relevant to chemistry. We introduce Gradient Guided Furthest P…
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…
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks
Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker +5
Physics-informed neural networks (PINNs) offer a powerful approach to solving partial differential equations (PDEs), which are ubiquitous in the quantitative sciences. Applied to b…
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…
On the Role of Pre-trained Embeddings in Binary Code Analysis
Alwin Maier, Felix Weissberg, Konrad Rieck
Deep learning has enabled remarkable progress in binary code analysis. In particular, pre-trained embeddings of assembly code have become a gold standard for solving analysis tasks…
Sparser, Better, Faster, Stronger: Sparsity Detection for Efficient Automatic Differentiation
Adrian Hill, Guillaume Dalle
From implicit differentiation to probabilistic modeling, Jacobian and Hessian matrices have many potential use cases in Machine Learning (ML), but they are viewed as computationall…
Enhancing Brain Source Reconstruction by Initializing 3D Neural Networks with Physical Inverse Solutions
Marco Morik, Ali Hashemi, Klaus-Robert Müller +2
Reconstructing brain sources is a fundamental challenge in neuroscience, crucial for understanding brain function and dysfunction. Electroencephalography (EEG) signals have a high…
Flow-Based Sampling for Entanglement Entropy and the Machine Learning of Defects
Andrea Bulgarelli, Elia Cellini, Karl Jansen +5
We introduce a novel technique to numerically calculate Rényi entanglement entropies in lattice quantum field theory using generative models. We describe how flow-based approaches…
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…
reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis
Kai Norman Clasen, Leonard Hackel, Tom Burgert +3
This paper presents refined BigEarthNet (reBEN) that is a large-scale, multi-modal remote sensing dataset constructed to support deep learning (DL) studies for remote sensing image…
MagicBathyNet: A Multimodal Remote Sensing Dataset for Bathymetry Prediction and Pixel-based Classification in Shallow Waters
Panagiotis Agrafiotis, Łukasz Janowski, Dimitrios Skarlatos +1
Accurate, detailed, and high-frequent bathymetry, coupled with complex semantic content, is crucial for the undermapped shallow seabed areas facing intense climatological and anthr…
A Label Propagation Strategy for CutMix in Multi-Label Remote Sensing Image Classification
Tom Burgert, Kai Norman Clasen, Jonas Klotz +2
The development of supervised deep learning-based methods for multi-label scene classification (MLC) is one of the prominent research directions in remote sensing (RS). However, co…
Combining Hammett constants for -machine learning and catalyst discovery
V. Diana Rakotonirina, Marco Bragato, Stefan Heinen +1
We study the applicability of the Hammett-inspired product (HIP) Ansatz to model relative substrate binding within homogenous organometallic catalysis, assigning and to lig…
Molecular relaxation by reverse diffusion with time step prediction
Khaled Kahouli, Stefaan Simon Pierre Hessmann, Klaus-Robert Müller +3
Molecular relaxation, finding the equilibrium state of a non-equilibrium structure, is an essential component of computational chemistry to understand reactivity. Classical force f…
A Dataset for Pharmacovigilance in German, French, and Japanese: Annotating Adverse Drug Reactions across Languages
Lisa Raithel, Hui-Syuan Yeh, Shuntaro Yada +11
User-generated data sources have gained significance in uncovering Adverse Drug Reactions (ADRs), with an increasing number of discussions occurring in the digital world. However,…
Estimating Physical Information Consistency of Channel Data Augmentation for Remote Sensing Images
Tom Burgert, Begüm Demir
The application of data augmentation for deep learning (DL) methods plays an important role in achieving state-of-the-art results in supervised, semi-supervised, and self-supervise…
Manifold GCN: Diffusion-based Convolutional Neural Network for Manifold-valued Graphs
Martin Hanik, Gabriele Steidl, Christoph von Tycowicz
We propose two graph neural network layers for graphs with features in a Riemannian manifold. First, based on a manifold-valued graph diffusion equation, we construct a diffusion l…
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
Luca Longo, Mario Brcic, Federico Cabitza +16
As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In respo…
LiT-4-RSVQA: Lightweight Transformer-based Visual Question Answering in Remote Sensing
Leonard Hackel, Kai Norman Clasen, Mahdyar Ravanbakhsh +1
Visual question answering (VQA) methods in remote sensing (RS) aim to answer natural language questions with respect to an RS image. Most of the existing methods require a large am…
Stress and heat flux via automatic differentiation
Marcel F. Langer, J. Thorben Frank, Florian Knoop
Machine-learning potentials provide computationally efficient and accurate approximations of the Born-Oppenheimer potential energy surface. This potential determines many materials…
An XAI framework for robust and transparent data-driven wind turbine power curve models
Simon Letzgus, Klaus-Robert Müller
Wind turbine power curve models translate ambient conditions into turbine power output. They are essential for energy yield prediction and turbine performance monitoring. In recent…
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…
Heat flux for semi-local machine-learning potentials
Marcel F. Langer, Florian Knoop, Christian Carbogno +2
The Green-Kubo (GK) method is a rigorous framework for heat transport simulations in materials. However, it requires an accurate description of the potential-energy surface and car…