7 citations · 8 across the 11 of their papers we have counts for
12 papers
A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty
Niklas Koenen, Claudia Battistin, Jeriek Van den Abeele +1
Modern probabilistic machine learning models increasingly produce multivariate outputs with complex dependence structure, from multi-step time-series forecasts to sample path predi…
A Hilbert-Valued Functional Decomposition Framework for Explaining Time-Dependent Outputs
Sophie Hanna Langbein, Niklas Koenen, Marvin N. Wright +1
Feature-based explanations quantify features' influence on model predictions, but are primarily designed for scalar outputs. In many applications, however, outputs are functional o…
LiD-GLM: Lipschitz-constrained Deep Generalized Linear Models
Tom Splittgerber, Niklas Koenen, Marvin N. Wright +1
The combination of traditional statistical models and neural network (NN) components into semi-structured hybrid models is an intriguing approach to construct models that, ideally,…
Functional Decomposition and Shapley Interactions for Interpreting Survival Models
Sophie Hanna Langbein, Hubert Baniecki, Fabian Fumagalli +3
Hazard and survival functions are natural, interpretable targets in time-to-event prediction, but their inherent non-additivity fundamentally limits standard additive explanation m…
Machine Learning in Epidemiology
Marvin N. Wright, Lukas Burk, Pegah Golchian +3
In the age of digital epidemiology, epidemiologists are faced by an increasing amount of data of growing complexity and dimensionality. Machine learning is a set of powerful tools…
What's Wrong with Your Synthetic Tabular Data? Using Explainable AI to Evaluate Generative Models
Jan Kapar, Niklas Koenen, Martin Jullum
Evaluating synthetic tabular data is challenging, since they can differ from the real data in so many ways. There exist numerous metrics of synthetic data quality, ranging from sta…
Gradient-based Explanations for Deep Learning Survival Models
Sophie Hanna Langbein, Niklas Koenen, Marvin N. Wright
Deep learning survival models often outperform classical methods in time-to-event predictions, particularly in personalized medicine, but their "black box" nature hinders broader a…
Conditional Feature Importance with Generative Modeling Using Adversarial Random Forests
Kristin Blesch, Niklas Koenen, Jan Kapar +4
This paper proposes a method for measuring conditional feature importance via generative modeling. In explainable artificial intelligence (XAI), conditional feature importance asse…
An Alternating Direction Method of Multipliers Algorithm for the Weighted Fused LASSO Signal Approximator
Louis Dijkstra, Moritz Hanke, Niklas Koenen +1
We present an Alternating Direction Method of Multipliers (ADMM) algorithm designed to solve the Weighted Generalized Fused LASSO Signal Approximator (wFLSA). First, we show that w…
Toward Understanding the Disagreement Problem in Neural Network Feature Attribution
Niklas Koenen, Marvin N. Wright
In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings…
Interpreting Deep Neural Networks with the Package innsight
Niklas Koenen, Marvin N. Wright
The R package innsight offers a general toolbox for revealing variable-wise interpretations of deep neural networks' predictions with so-called feature attribution methods. Aside f…
Generalization of the Change of Variables Formula with Applications to Residual Flows
Niklas Koenen, Marvin N. Wright, Peter Maaß +1
Normalizing flows leverage the Change of Variables Formula (CVF) to define flexible density models. Yet, the requirement of smooth transformations (diffeomorphisms) in the CVF pose…