203 citations · 461 across the 14 of their papers we have counts for
16 papers
Stability-Shaped Deep Graph Learning
Junyou Zhu, Langzhou He, Fenying Cai +7
In deep graph neural networks, increasing depth enlarges the receptive field but often leads to over-smoothing, where node representations tend to align. We develop a unified, mode…
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…
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…
Mark My Words: Dangers of Watermarked Images in ImageNet
Kirill Bykov, Klaus-Robert Müller, Marina M. -C. Höhne
The utilization of pre-trained networks, especially those trained on ImageNet, has become a common practice in Computer Vision. However, prior research has indicated that a signifi…
Reconstructing Kernel-based Machine Learning Force Fields with Super-linear Convergence
Stefan Blücher, Klaus-Robert Müller, Stefan Chmiela
Kernel machines have sustained continuous progress in the field of quantum chemistry. In particular, they have proven to be successful in the low-data regime of force field reconst…
Automatic Identification of Chemical Moieties
Jonas Lederer, Michael Gastegger, Kristof T. Schütt +3
In recent years, the prediction of quantum mechanical observables with machine learning methods has become increasingly popular. Message-passing neural networks (MPNNs) solve this…
Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
Ludwig Winkler, Klaus-Robert Müller, Huziel E. Sauceda
Molecular dynamics simulations are a cornerstone in science, allowing to investigate from the system's thermodynamics to analyse intricate molecular interactions. In general, to cr…
Inverse design of 3d molecular structures with conditional generative neural networks
Niklas W. A. Gebauer, Michael Gastegger, Stefaan S. P. Hessmann +2
The rational design of molecules with desired properties is a long-standing challenge in chemistry. Generative neural networks have emerged as a powerful approach to sample novel m…
Explaining Bayesian Neural Networks
Kirill Bykov, Marina M. -C. Höhne, Adelaida Creosteanu +4
To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predicti…
Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization
Léo Andeol, Yusei Kawakami, Yuichiro Wada +3
Domain shifts in the training data are common in practical applications of machine learning; they occur for instance when the data is coming from different sources. Ideally, a ML m…
SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
Oliver T. Unke, Mihail Bogojeski, Michael Gastegger +3
Machine learning has enabled the prediction of quantum chemical properties with high accuracy and efficiency, allowing to bypass computationally costly ab initio calculations. Inst…
Machine learning of solvent effects on molecular spectra and reactions
Michael Gastegger, Kristof T. Schütt, Klaus-Robert Müller
Fast and accurate simulation of complex chemical systems in environments such as solutions is a long standing challenge in theoretical chemistry. In recent years, machine learning…
Towards CRISP-ML(Q): A Machine Learning Process Model with Quality Assurance Methodology
Stefan Studer, Thanh Binh Bui, Christian Drescher +4
Machine learning is an established and frequently used technique in industry and academia but a standard process model to improve success and efficiency of machine learning applica…
Explaining and Interpreting LSTMs
Leila Arras, Jose A. Arjona-Medina, Michael Widrich +5
While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the v…
Local Function Complexity for Active Learning via Mixture of Gaussian Processes
Danny Panknin, Stefan Chmiela, Klaus-Robert Müller +1
Inhomogeneities in real-world data, e.g., due to changes in the observation noise level or variations in the structural complexity of the source function, pose a unique set of chal…
Investigating the influence of noise and distractors on the interpretation of neural networks
Pieter-Jan Kindermans, Kristof Schütt, Klaus-Robert Müller +1
Understanding neural networks is becoming increasingly important. Over the last few years different types of visualisation and explanation methods have been proposed. However, none…