10.07.2024

Teaser image to

MCML Researchers With Three Papers at UAI 2024

40th Conference on Uncertainty in Artificial Intelligence (UAI 2024). Barcelona, Spain, 15.07.2024–19.07.2024

We are happy to announce that MCML researchers are represented with three papers at UAI 2024. Congrats to our researchers!

Main Track (3 papers)

C. Damke and E. Hüllermeier.
Linear Opinion Pooling for Uncertainty Quantification on Graphs.
UAI 2024 - 40th Conference on Uncertainty in Artificial Intelligence. Barcelona, Spain, Jul 16-18, 2024. URL GitHub
Abstract

We address the problem of uncertainty quantification for graph-structured data, or, more specifically, the problem to quantify the predictive uncertainty in (semi-supervised) node classification. Key questions in this regard concern the distinction between two different types of uncertainty, aleatoric and epistemic, and how to support uncertainty quantification by leveraging the structural information provided by the graph topology. Challenging assumptions and postulates of state-of-the-art methods, we propose a novel approach that represents (epistemic) uncertainty in terms of mixtures of Dirichlet distributions and refers to the established principle of linear opinion pooling for propagating information between neighbored nodes in the graph. The effectiveness of this approach is demonstrated in a series of experiments on a variety of graph-structured datasets.

MCML Authors
Link to website

Clemens Damke

Artificial Intelligence and Machine Learning

Link to Profile Eyke Hüllermeier

Eyke Hüllermeier

Prof. Dr.

Artificial Intelligence and Machine Learning


L. Kook, C. Kolb, P. Schiele, D. Dold, M. Arpogaus, C. Fritz, P. Baumann, P. Kopper, T. Pielok, E. Dorigatti and D. Rügamer.
How Inverse Conditional Flows Can Serve as a Substitute for Distributional Regression.
UAI 2024 - 40th Conference on Uncertainty in Artificial Intelligence. Barcelona, Spain, Jul 16-18, 2024. URL
Abstract

Neural network representations of simple models, such as linear regression, are being studied increasingly to better understand the underlying principles of deep learning algorithms. However, neural representations of distributional regression models, such as the Cox model, have received little attention so far. We close this gap by proposing a framework for distributional regression using inverse flow transformations (DRIFT), which includes neural representations of the aforementioned models. We empirically demonstrate that the neural representations of models in DRIFT can serve as a substitute for their classical statistical counterparts in several applications involving continuous, ordered, time-series, and survival outcomes. We confirm that models in DRIFT empirically match the performance of several statistical methods in terms of estimation of partial effects, prediction, and aleatoric uncertainty quantification. DRIFT covers both interpretable statistical models and flexible neural networks opening up new avenues in both statistical modeling and deep learning.

MCML Authors
Link to website

Chris Kolb

Statistical Learning and Data Science

Link to website

Tobias Pielok

Statistical Learning and Data Science

Link to Profile David Rügamer

David Rügamer

Prof. Dr.

Statistics, Data Science and Machine Learning


Y. Sale, P. Hofman, T. Löhr, L. Wimmer, T. Nagler and E. Hüllermeier.
Label-wise Aleatoric and Epistemic Uncertainty Quantification.
UAI 2024 - 40th Conference on Uncertainty in Artificial Intelligence. Barcelona, Spain, Jul 16-18, 2024. URL
Abstract

We present a novel approach to uncertainty quantification in classification tasks based on label-wise decomposition of uncertainty measures. This label-wise perspective allows uncertainty to be quantified at the individual class level, thereby improving cost-sensitive decision-making and helping understand the sources of uncertainty. Furthermore, it allows to define total, aleatoric, and epistemic uncertainty on the basis of non-categorical measures such as variance, going beyond common entropy-based measures. In particular, variance-based measures address some of the limitations associated with established methods that have recently been discussed in the literature. We show that our proposed measures adhere to a number of desirable properties. Through empirical evaluation on a variety of benchmark data sets – including applications in the medical domain where accurate uncertainty quantification is crucial – we establish the effectiveness of label-wise uncertainty quantification.

MCML Authors
Link to website

Yusuf Sale

Artificial Intelligence and Machine Learning

Link to website

Paul Hofman

Artificial Intelligence and Machine Learning

Link to website

Lisa Wimmer

Statistical Learning and Data Science

Link to Profile Thomas Nagler

Thomas Nagler

Prof. Dr.

Computational Statistics & Data Science

Link to Profile Eyke Hüllermeier

Eyke Hüllermeier

Prof. Dr.

Artificial Intelligence and Machine Learning


10.07.2024


Subscribe to RSS News feed

Related

Link to AI for better Social Media - with researcher Dominik Bär

04.08.2025

AI for Better Social Media - With Researcher Dominik Bär

Dominik Bär develops AI for real-time counterspeech to combat hate and misinformation, part of the KI Trans project on AI in education.

Link to Fabian Theis receives 2025 ISCB Innovator Award

01.08.2025

Fabian Theis Receives 2025 ISCB Innovator Award

Fabian Theis receives 2025 ISCB Innovator Award for advancing AI in biology and mentoring the next generation of scientists.

Link to Tracking Our Changing Planet from Space - with Xiaoxiang Zhu

30.07.2025

Tracking Our Changing Planet From Space - With Xiaoxiang Zhu

In this video, Xiaoxiang Zhu shares how her team extracts geo-information from petabytes of data, with real impact on global challenges.

Link to Yusuf Sale receives IJAR Young Researcher Award

29.07.2025

Yusuf Sale Receives IJAR Young Researcher Award

MCML Junior Member Yusuf Sale received an IJAR Young Researcher Award at ISIPTA 2025 for his work.

Link to Barbara Plank awarded 2025 Imminent Research Grant for work on language data

29.07.2025

Barbara Plank Awarded 2025 Imminent Research Grant for Work on Language Data

Barbara Plank’s MaiNLP lab wins 2025 Imminent Research Grant for a project on language data with Peng and de Marneffe.