Multi-Target Prediction With Deep Neural Networks: A Hands-on Tutorial

ECML/PKDD 2022, Grenoble, France on September 19th, 2022


Overview of the tutorial

Over the last decade, multi-target prediction (MTP) has emerged as a novel umbrella term, unifying supervised learning techniques that are concerned with predicting multiple target variables at the same time. In principle, these targets can be of different types, such as nominal, ordinal, or real-valued. Driven by tutorials and workshops at international conferences, such as ICML 2013 and ECML/PKDD 2014, 2015 and 2018, the area of MTP has attracted significant interest in the machine learning community. Its applicability potential is continuously increasing, as more and more real-world problems require the simultaneous prediction of multiple targets.

In the field of machine learning one can identify many classical examples of MTP tasks, such as the image tagging task from the area of computer vision, the document tagging task from the field of text mining, as well as the product recommendation task that is prevalent in online retailing. In addition to these typical examples, one can also identify instances of MTP-related applications that are less well known yet important. In the field of climate science, forecasting the weather in different areas of the world at the same time is a quite complicated task that necessitates the modeling of relationships between various atmospheric processes. In medicine, patients can usually be associated with multiple interacting pathologies at the same time. Finally, the emergence of the latest pandemic has highlighted the importance of rapid drug discovery. In this field, the initial goal is to find a set of chemical compounds that show high binding affinity with a biological target, so the use of automated multi-target prediction methods can provide a much-needed speedup.

A recent survey (Waegeman et al. 2019) reviewed not less than 100 methods from these subfields from a general multi-target prediction perspective. In addition, a formal mathematical framework to gather those subfields under a single umbrella was expounded. This mathematical framework will be the point of departure for this tutorial, which is the discussion of a general deep learning methodology for multi-target prediction problems. Unlike previous tutorials on multi-target prediction, we do not intend to give a historical perspective of multi-target prediction. In contrast, we would like to focus on recent developments in the area of deep learning. Our tutorial will include a hands-on part, in which participants can play with several neural network architectures for multi-target prediction.


Willem Waegeman, Ghent University, Belgium
Dimitrios Iliadis, Ghent University, Belgium

Target audience

With the tutorial we aim to attract both researchers that are already active in one of the above domains, as well as researchers with little or no prior experience in multi-target prediction. We will only assume a general familiarity with well-known machine learning techniques for classification and regression (neural networks, feature learning, risk minimization, hyperparameter optimization, etc.). As such, we believe that the tutorial will attract attendees from diverse subfields of machine learning and with different background.


Can be found here.

Previous initiatives

Tutorial on Multi-Target Prediction, ECML/PKDD 2018 link
International Workshop on Big Multi-Target Prediction, ECML/PKDD 2015 link
International Workshop on Multi-Target Prediction, ECML/PKDD 2014 link
Tutorial on Multi-Target Prediction, ICML 2013 link