09.30 Registration opens (Senatssaal)
10.00 - 12.00 Pre-Workshop Tutorial on Uncertainty
12.15 - 12.30 Welcome & Opening
12.30 - 13.30 Invited Talk: Meelis Kull
13.30 - 15.00 Presentations
15.00 - 15.30 Coffee Break
15.30 - 16.30 Presentations
16.30 - 18.00 Poster Session 1
09.00 - 10.00 Invited Talk: Sébastien Destercke
10.00 - 10.30 Presentations
10.30 - 11.00 Coffee Break
11.00 - 13.00 Presentations
13.00 - 14.00 Lunch Break
14.00 - 15.30 Presentations
15.30 - 16.00 Coffee Break
16.00 - 17.30 Poster Session 2
09.00 - 10.30 Presentations
10.30 - 11.00 Coffee Break
11.00 - 13.00 Presentations
13.00 - 14.00 Lunch Break
14.00 - 14.15 Closing
14.15 - 16.00 Informal discussions & project meetings
Bio: Meelis Kull is an associate professor of machine learning at the University of Tartu and the Head of the Estonian Centre of Excellence in Artificial Intelligence. He has a PhD from the University of Tartu and did a postdoc at the University of Bristol where he is an honorary senior research associate. His research interests include uncertainty quantification and calibration in machine learning and the trustworthiness of learning-based AI systems. He enjoys theoretical research with a clear path to applications.
Bio: Sébastien Destercke graduated from the Faculté Polytechnique de Mons as an Engineer with a specialization in computer science and applied mathematics. He then did a PhD in risk analysis for nuclear safety, under the supervision of Didier Dubois (IRIT, Toulouse) and Eric Chojnacki (IRSN, Cadarache), where he started his research in the field of uncertainty modelling and reasoning in situations of severe uncertainty, focusing on issues related to uncertainty representation, information fusion and uncertainty propagation. After spending two years as a research engineer in an agronomical institute (developing aid-decision tools), he joined the CNRS (of which he is now a senior researcher) and the Heudiasyc laboratory, where he started to investigate the links between machine learning and severe uncertainty modelling. Sébastien research focuses on the use of uncertainty theories that generalise and enrich classical probabilities and sets, trying to share his time between more theoretical and more applied research.
Willem Waegeman is Associate professor at the Department of Data Analysis and Mathematical Modelling of the Faculty of Bioscience Engineering of Ghent University. He is member of of the Knowledge-based Systems research unit KERMIT. His research activities are centred on machine learning and data science, including theoretical research and various applications in the life sciences. Specific areas of interest are multi-target prediction, deep learning, sequence models, and time series analysis.
Eyke Hüllermeier is a full professor at the Institute of Informatics at LMU Munich, Germany, where he heads the Chair of Artificial Intelligence and Machine Learning. He studied mathematics and business computing, received his PhD in computer science from Paderborn University in 1997, and a Habilitation degree in 2002. Prior to joining LMU, he spent two years as a Marie Curie fellow at the IRIT in Toulouse (France) and held professorships at the Universities of Dortmund, Magdeburg, Marburg, and Paderborn.
His research interests are centered around methods and theoretical foundations of artificial intelligence, with a specific focus on machine learning and reasoning under uncertainty. He has published more than 300 articles on these topics in top-tier journals and major international conferences, and several of his contributions have been recognized with scientific awards. Professor Hüllermeier is President of the European Association for Data Science (EuADS) and Editor-in-Chief of Data Mining and Knowledge Discovery, one of the leading journals in the field of AI. He also serves on the editorial board of several other journals, including Machine Learning, Journal of Machine Learning Research, IEEE Computational Intelligence Magazine, Artificial Intelligence Review, and the International Journal of Approximate Reasoning.
Viacheslav Komisarenko, Estonia, University of Tartu: On Calibration Improvement with Focal Activation
Markus Kängsepp, Estonia, University of Tartu: Calibrated Perception Uncertainty Across Objects and Regions in Bird’s-Eye-View
Novin Shahroudi, Estonia, University of Tartu: Evaluation of Trajectory Distribution Predictions with Energy Score
Predicting the future trajectory of surrounding objects is inherently uncertain and vital in the safe and reliable planning of autonomous systems such as self-driving cars. Although trajectory prediction models have become increasingly sophisticated in dealing with the complexities of spatiotemporal data, the evaluation methods used to assess these models have not kept pace. "Minimum of N" is a common family of metrics used to assess such rich outputs. We critically examine the Minimum of N within the proper scoring rules framework to show that it is not strictly proper and demonstrate how that could lead to an uninformative and even misleading assessment of multimodal trajectory predictions. As an alternative, we propose using Energy Score-based evaluation measures, leveraging their proven propriety for a more reliable evaluation of trajectory distribution predictions.
David Rügamer, Germany, MCML, LMU Munich: Towards Tractable Bayesian Deep Learning
Göran Kauermann, Germany, LMU Munich: Labeling Uncertainty
Thomas Augustin , Germany, LMU Munich: Machine learning under measurement error --- yesterday's concerns or renaissance of a classical sub-discipline?
The talk looks at machine learning under noisy data from a measurement error perspective, which has been developed in statistical modelling in biometrics, econometrics and psychometrics since the eighties of the last century. We discuss the folklore statement that measurement error is no longer an issue after the prediction-oriented turn in data science. In doing so, we argue from an interpretable machine learning and a privacy preserving machine learning perspective. To make the argumentation a bit more concrete and technical, we then look at measurement error in recursive partitioning. We discuss structural effects of measurement error in regression trees and finally derive a corrected score function in the context of model-based recursive partitioning of survival data.
Slides
Christian Fröhlich, Germany, University of Tübingen: Data Models With Underlying Imprecision
Most work in the field of imprecise probabilities has been rooted in the subjectivist paradigm. We aim to revive two largely discontinued threads of research on imprecision from a frequentist perspective. We mainly focus on constructing data models which exhibit true underlying imprecision, that is, where the imprecision is not due to epistemic uncertainty, but inherent to the data generating process. Such data models then pave the way for deriving generalizations of concepts like calibration and scoring rules, notions which we claim are only meaningful relative to a data model. As to applications, it turns out that this view on imprecision can be meaningfully linked to the machine learning literature on learning from multiple distributions.
Andrea Campagner, Italy , IRCCS Ospedale Galeazzi Sant'Ambrogio: Credal Learning: Weakly Supervised Learning from Credal Sets
Michele Caprio and Kuk Jin Jang , USA, University of Pennsylvania: Imprecise Evidential Classification
Uncertainty quantification presents a pivotal challenge in the field of artificial intelligence, profoundly impacting decision-making, risk assessment, and model reliability. In this paper, we introduce Imprecise Evidential Neural Networks (IENN) as a novel approach to address this challenge in classification tasks. IENN leverages a credal set of evidential predictive distributions. They allow to avoid overfitting to the training data, and to systematically assess both epistemic and aleatoric uncertainties (EU and AU, respectively). When these uncertainties surpass acceptable thresholds, IENN has the capability to abstain from classification and indicate an excess of EU or AU. Conversely, within acceptable uncertainty bounds, IENN provides a label class with robust probabilistic guarantees. IENN is trained using standard backpropagation and a loss function that draws from the theory of evidence. Our approach overcomes the shortcomings of previous efforts, and extends the current evidential deep learning literature. Through extensive experiments, we demonstrate the competitive performance of IENN in classification with abstention and out-of-distribution (OOD) evaluation settings, showcasing its effectiveness on benchmark datasets.
Volker Tresp, Germany, LMU Munich: Where Heisenberg, and not Bayes, Rules
Tanmoy Mukherjee, Belgium, University of Antwerp/imec: OOD Detection and the Tale of Two Uncertainties
David Strieder, Germany, MCML, TUM: Confidence in Causal Inference under Structure Uncertainty
Inferring the effect of interventions within complex systems is a fundamental problem of statistics. A widely studied approach employs structural causal models that postulate noisy functional relations among a set of interacting variables. The underlying causal structure is then naturally represented by a directed graph whose edges indicate direct causal dependencies. In a recent line of work, additional assumptions on the causal models have been shown to render this causal graph identifiable from observational data alone. One example is the assumption of linear causal relations with homoscedastic errors that we will take up in this work. When the graph structure is known, classical methods may be used for calculating estimates and confidence intervals for causal effects. However, in many applications, expert knowledge that provides an a priori valid causal structure is not available. Lacking alternatives, a commonly used two-step approach first learns a graph and then treats the graph as known in inference. This, however, yields confidence intervals that are overly optimistic and fail to account for the data-driven model choice. We argue that to draw reliable conclusions, it is necessary to incorporate the remaining uncertainty about the underlying causal structure in confidence statements about causal effects. To address this issue, we present a framework based on test inversion that allows us to give confidence regions for total causal effects that capture both sources of uncertainty: causal structure and numerical size of nonzero effects.
Nis Meinert, Germany, German Aerospace Center (DLR): Your Epistemic Uncertainty is Secretly a Density Estimation and You Should Treat it Like One
Mira Jürgens, Belgium, Ghent University: Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
In recent years, evidential deep learning methods have become a popular approach of quantifying epistemic (and aleatoric) uncertainty. The resulting second-order distributions are obtained by a single forward-pass of a second-order learner, which is trained in a direct way. In this talk, we will investigate whether the resulting distributions represent epistemic uncertainty in a faithful manner. To this end, we will introduce the notion of a reference distribution and argue that second-order methods should provide an estimate of this distribution if they intend to model epistemic uncertainty in a frequentist way. We both theoretically and empirically show that this is often not the case.
Bálint Mucsanyi, Germany, University of Tübingen: Are Uncertainty Quantification Methods Doing What We Think They Are Doing?
In recent years, a multitude of uncertainty quantification methods have been developed with different ideas in mind. In this paper, we wonder if they are doing what they are intended to do. We benchmark widely used uncertainty quantification methods on various practical tasks ranging from out-of-distribution detection to abstained prediction. We also investigate the performance of uncertainty disentanglement methods on real-life tasks, the correlation of their components, and the alignment of popular uncertainty estimators with these components. We find that simple uncertainty often estimators dominate on the practical tasks and that the performance of the methods is saturated. We further observe that, although uncertainty disentanglement methods might be principled, their components are not disentangled in our experiments.
Konstantin Hess, Germany, LMU Munich: Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
Treatment effect estimation in continuous time is crucial for personalized medicine. However, existing methods for this task are limited to point estimates of the potential outcomes, whereas uncertainty estimates have been ignored. Needless to say, uncertainty quantification is crucial for reliable decision-making in medical applications. To fill this gap, we propose a novel Bayesian Neural Controlled Differential Equations for treatment effect estimation in continuous time. In our \method, the time dimension is modeled through a coupled system of neural controlled differential equations and neural stochastic differential equations, where the neural stochastic differential equations allow for tractable variational Bayesian inference. Thereby, for an assigned sequence of treatments, our \method provides meaningful posterior predictive distributions of the potential outcomes. To the best of our knowledge, ours is the first tailored neural method to provide uncertainty estimates of treatment effects in continuous time. As such, our method is of direct practical value for promoting reliable decision-making in medicine.
Nikos Nikolaou, United Kingdom, University College London: On the Interplay Between Uncertainty Quantification and Model Explainability
Nina Schmid, Germany, University of Bonn: Advancing Uncertainty Quantification in Universal Differential Equations: Formulation, Assessment, and Comparison
Universal Differential Equations for ScientificMachine Learning (UDEs) are a dynamic mod-elling approach to combine prior knowledge inform of mechanistic formulations with univer-sal function approximators, like neural networks.The neural network component is used to describeunknown components of a differential equation.The estimation of uncertainty, with respect to plau-sible values of mechanistic parameters, as wellas the prediction uncertainty of the whole modelor model components, is crucial for the interpre-tation of the modeling results. With this work,we attempt a formalisation of uncertainty quantifi-cation (UQ) for UDEs and investigate importantfrequentist and Bayesian methods. By analyzingthree synthetic examples of increasing complexityand estimating the underlying ground truth uncer-tainty, we evaluate the validity and efficiency ofdifferent UQ methods.
Cornelia Gruber, Germany, LMU Munich: More Labels or Cases? Assessing Label Variation in Natural Language Inference
In this work, we analyze the uncertainty that is inherently present in the labels used for supervised machine learning in natural language inference (NLI). In cases where multiple annotations per instance are available, neither the majority vote nor the frequency of individual class votes is a trustworthy representation of the labeling uncertainty.
We propose modeling the votes via a Bayesian mixture model to recover the data-generating process, i.e., the posterior distribution of the "true" latent classes, and thus gain insight into the class variations. This will enable a better understanding of the confusion happening during the annotation process. We also assess the stability of the proposed estimation procedure by systematically varying the numbers of i) instances and ii) labels. Thereby, we observe that few instances with many labels can predict the latent class borders reasonably well, while the estimation fails for many instances with only a few labels. This leads us to conclude that multiple labels are a crucial building block for properly analyzing label uncertainty.
Alaa Othman, Center for Applied Data Science Gütersloh (CfADS) Hochschule Bielefeld-University of Applied Sciences
Andrea Belles Ferreres, German Aerospace Center (DLR)
Miro Miranda Lorenz, German Research Center for Artificial Intelligence, University of Kaiserslautern-Landau
Thomas Mortier, Ghent University
Paul Hofman, LMU Munich
Amir Hossein Kargaran, LMU Munich
Valentin Margraf, LMU Munich
Sepideh Saran, Max Delbrueck Center / Technical University of Berlin
Alessandro Scagliotti, MCML, TUM
Frederik Hoppe, RWTH Aachen University
Dominik Fuchsgruber, TUM
Viacheslav Komisarenko, University of Tartu
Markus Kängsepp, University of Tartu
Novin Shahroudi, University of Tartu
Kornelius Raeth, University of Tübingen
Alireza Javanmardi, LMU Munich
Nina Maria Gottschling, German Aerospace Center (DLR)
Ghifari Adam Faza, KU Leuven
Kaizheng Wang, KU Leuven
Cornelia Gruber, LMU Munich
Raziyeh Hosseini, LMU Munich
Leonardo Galli, LMU Munich
Long XUE, The Hong Kong Polytechnic University
Carina Newen, TU Dortmund
Nikos Nikolaou, University College London
Tanmoy Mukherjee, University of Antwerp/imec
Corrado Mencar, University of Bari Aldo Moro
Cornelius Emde, University of Oxford
Mihkel Lepson, University of Tartu
Joonas Järve, University of Tartu
Michael Deistler, University of Tübingen
Matias Pizarro, Ruhr Universität & Dorothea Kolossa, TU Berlin