ECML/PKDD 2020 Tutorial and Workshop on Uncertainty in Machine Learning (18th september)


  • 18-09-2020: worskshop is on-going, if you want to join in zoom, click here

  • 28-08-2020: a tentative program is now online. Check the Program page!

  • 23-07-2020: after selection, the workshop will have 10 long and 4 short presentations, for a total of 14 accepted papers

  • 20-04-2020: we are happy to announce our first invited speaker, in the person of Meelis Kull. Thanks to him for having accepted our invitation!

Motivation and Focus

The notion of uncertainty is of major importance in machine learning and constitutes a key element of modern machine learning methodology. In recent years, it has gained in importance due to the increasing relevance of machine learning for practical applications, many of which are coming with safety requirements. In this regard, new problems and challenges have been identified by machine learning scholars, which call for new methodological developments. Indeed, while uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions, recent research has gone beyond traditional approaches and also leverages more general formalisms and uncertainty calculi. For example, a distinction between different sources and types of uncertainty, such as aleatoric and epistemic uncertainty, turns out to be useful in many machine learning applications. The workshop will pay specific attention to recent developments of this kind.

This workshop will be preceded by a tutorial, which provides an introduction to the topic of uncertainty in machine learning and gives an overview of existing methods and hitherto approaches to dealing with uncertainty.

Aim and Scope

The goal of this workshop is to bring together researchers interested in the topic of uncertainty in machine learning. It is meant to provide a forum for the discussion of the most recent developments in the modeling, processing, and quantification of uncertainty in machine learning problems, and the exploration of new research directions in this field. We welcome papers on all facets of uncertainty in machine learning. We solicit original work, which can be theoretical, practical, or applied, and also encourage the submission of work in progress as well as position papers or critical notes.

Topics of interests

The scope of the workshop covers, but is not limited to, the following topics:

  • adversarial examples

  • belief functions

  • calibration

  • classification with reject option

  • conformal prediction

  • credal classifiers

  • deep learning and neural networks

  • ensemble methods

  • epistemic uncertainty

  • imprecise probability

  • likelihood and fiducial inference

  • model selection and misspecification

  • multi-armed bandits

  • online learning

  • noisy data and outliers

  • out-of-sample prediction

  • performance evaluation

  • hypothesis testing

  • probabilistic methods

  • Bayesian machine learning

  • reliable prediction

  • set-valued prediction

  • uncertainty quantification