Home | Research | Groups | Niki Kilbertus

Research Group Niki Kilbertus

Link to Niki Kilbertus

Niki Kilbertus

Prof. Dr.

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Niki Kilbertus

is Assistant Professor of Ethics in Systems Design and Machine Learning at TU Munich.

He and his team investigate the interactions between machine learning algorithms and humans with a focus on ethical consequences and trustworthiness. They currently study identification and estimation of causal effects from observational data in automated decision-making and dynamic environments.

Team members @MCML

Link to Elisabeth Ailer

Elisabeth Ailer

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Sören Becker

Sören Becker

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Cecilia Casolo

Cecilia Casolo

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Birgit Kühbacher

Birgit Kühbacher

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Zhufeng Li

Zhufeng Li

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Jiaqi Lu

Jiaqi Lu

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Kirtan Padh

Kirtan Padh

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Nora Schneider

Nora Schneider

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Publications @MCML

[5]
E. Ailer, N. Dern, J. Hartford and N. Kilbertus.
Targeted Sequential Indirect Experiment Design.
38th Conference on Neural Information Processing Systems (NeurIPS 2024). Vancouver, Canada, Dec 10-15, 2024. To be published. Preprint at arXiv. arXiv.
Abstract

Scientific hypotheses typically concern specific aspects of complex, imperfectly understood or entirely unknown mechanisms, such as the effect of gene expression levels on phenotypes or how microbial communities influence environmental health. Such queries are inherently causal (rather than purely associational), but in many settings, experiments can not be conducted directly on the target variables of interest, but are indirect. Therefore, they perturb the target variable, but do not remove potential confounding factors. If, additionally, the resulting experimental measurements are multi-dimensional and the studied mechanisms nonlinear, the query of interest is generally not identified. We develop an adaptive strategy to design indirect experiments that optimally inform a targeted query about the ground truth mechanism in terms of sequentially narrowing the gap between an upper and lower bound on the query. While the general formulation consists of a bi-level optimization procedure, we derive an efficiently estimable analytical kernel-based estimator of the bounds for the causal effect, a query of key interest, and demonstrate the efficacy of our approach in confounded, multivariate, nonlinear synthetic settings.

MCML Authors
Link to Elisabeth Ailer

Elisabeth Ailer

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Niki Kilbertus

Niki Kilbertus

Prof. Dr.

Ethics in Systems Design and Machine Learning

A3 | Computational Models


[4]
S. d'Ascoli, S. Becker, P. Schwaller, A. Mathis and N. Kilbertus.
ODEFormer: Symbolic Regression of Dynamical Systems with Transformers.
12th International Conference on Learning Representations (ICLR 2024). Vienna, Austria, May 07-11, 2024. URL. GitHub.
Abstract

We introduce ODEFormer, the first transformer able to infer multidimensional ordinary differential equation (ODE) systems in symbolic form from the observation of a single solution trajectory. We perform extensive evaluations on two datasets: (i) the existing ‘Strogatz’ dataset featuring two-dimensional systems; (ii) ODEBench, a collection of one- to four-dimensional systems that we carefully curated from the literature to provide a more holistic benchmark. ODEFormer consistently outperforms existing methods while displaying substantially improved robustness to noisy and irregularly sampled observations, as well as faster inference.

MCML Authors
Link to Sören Becker

Sören Becker

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Niki Kilbertus

Niki Kilbertus

Prof. Dr.

Ethics in Systems Design and Machine Learning

A3 | Computational Models


[3]
L. Eyring, D. Klein, T. Uscidda, G. Palla, N. Kilbertus, Z. Akata and F. J. Theis.
Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation.
12th International Conference on Learning Representations (ICLR 2024). Vienna, Austria, May 07-11, 2024. URL.
Abstract

In optimal transport (OT), a Monge map is known as a mapping that transports a source distribution to a target distribution in the most cost-efficient way. Recently, multiple neural estimators for Monge maps have been developed and applied in diverse unpaired domain translation tasks, e.g. in single-cell biology and computer vision. However, the classic OT framework enforces mass conservation, which makes it prone to outliers and limits its applicability in real-world scenarios. The latter can be particularly harmful in OT domain translation tasks, where the relative position of a sample within a distribution is explicitly taken into account. While unbalanced OT tackles this challenge in the discrete setting, its integration into neural Monge map estimators has received limited attention. We propose a theoretically grounded method to incorporate unbalancedness into any Monge map estimator. We improve existing estimators to model cell trajectories over time and to predict cellular responses to perturbations. Moreover, our approach seamlessly integrates with the OT flow matching (OT-FM) framework. While we show that OT-FM performs competitively in image translation, we further improve performance by incorporating unbalancedness (UOT-FM), which better preserves relevant features. We hence establish UOT-FM as a principled method for unpaired image translation.

MCML Authors
Link to Luca Eyring

Luca Eyring

Interpretable and Reliable Machine Learning

B1 | Computer Vision

Link to Niki Kilbertus

Niki Kilbertus

Prof. Dr.

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Zeynep Akata

Zeynep Akata

Prof. Dr.

Interpretable and Reliable Machine Learning

B1 | Computer Vision

Link to Fabian Theis

Fabian Theis

Prof. Dr.

Mathematical Modelling of Biological Systems

C2 | Biology


[2]
S. Feuerriegel, D. Frauen, V. Melnychuk, J. Schweisthal, K. Hess, A. Curth, S. Bauer, N. Kilbertus, I. S. Kohane and M. van der Schaar.
Causal machine learning for predicting treatment outcomes.
Nature Medicine 30 (Apr. 2024). DOI.
Abstract

Causal machine learning (ML) offers flexible, data-driven methods for predicting treatment outcomes including efficacy and toxicity, thereby supporting the assessment and safety of drugs. A key benefit of causal ML is that it allows for estimating individualized treatment effects, so that clinical decision-making can be personalized to individual patient profiles. Causal ML can be used in combination with both clinical trial data and real-world data, such as clinical registries and electronic health records, but caution is needed to avoid biased or incorrect predictions. In this Perspective, we discuss the benefits of causal ML (relative to traditional statistical or ML approaches) and outline the key components and steps. Finally, we provide recommendations for the reliable use of causal ML and effective translation into the clinic.

MCML Authors
Link to Stefan Feuerriegel

Stefan Feuerriegel

Prof. Dr.

Artificial Intelligence in Management

C4 | Computational Social Sciences

Link to Dennis Frauen

Dennis Frauen

Artificial Intelligence in Management

C4 | Computational Social Sciences

Link to Valentyn Melnychuk

Valentyn Melnychuk

Artificial Intelligence in Management

C4 | Computational Social Sciences

Link to Jonas Schweisthal

Jonas Schweisthal

Artificial Intelligence in Management

C4 | Computational Social Sciences

Link to Stefan Bauer

Stefan Bauer

Prof. Dr.

Algorithmic Machine Learning & Explainable AI

A1 | Statistical Foundations & Explainability

Link to Niki Kilbertus

Niki Kilbertus

Prof. Dr.

Ethics in Systems Design and Machine Learning

A3 | Computational Models


[1]
L. Hetzel, S. Boehm, N. Kilbertus, S. Günnemann, M. Lotfollahi and F. J. Theis.
Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution.
36th Conference on Neural Information Processing Systems (NeurIPS 2022). New Orleans, LA, USA, Nov 28-Dec 09, 2022. PDF.
MCML Authors
Link to Leon Hetzel

Leon Hetzel

Mathematical Modelling of Biological Systems

C2 | Biology

Link to Niki Kilbertus

Niki Kilbertus

Prof. Dr.

Ethics in Systems Design and Machine Learning

A3 | Computational Models

Link to Stephan Günnemann

Stephan Günnemann

Prof. Dr.

Data Analytics & Machine Learning

A3 | Computational Models

Link to Fabian Theis

Fabian Theis

Prof. Dr.

Mathematical Modelling of Biological Systems

C2 | Biology