About the workshop
Deep learning for irregular time series is a vital research area focused on building machine learning models that handle data with irregular sampling, missing values, noise, and multiresolution characteristics. These challenges are common in real-world domains like finance, healthcare, and environmental science. Robust models must be trustworthy, with explainability and uncertainty quantification playing a central role—especially in high-stakes decisions.
This workshop addresses scenarios where data is either scarce or labels are limited, requiring modern AI solutions that "do more with less." Key challenges include heterogeneity, multiresolution, and sparsity in time series data. Our aim is to advance state-of-the-art techniques that tackle:
- Short time series with limited history
- Multiresolution and heterogeneous signals
- Noisy and missing data
- Scarcely labeled or unlabeled data
The ML4ITS workshop builds on previous successful editions at ECML-PKDD and continues to foster idea exchange in designing effective machine learning models for irregular time series. We invite submissions on:
- Generative models (e.g., GANs, diffusion, masked modeling)
- Self-supervised and unsupervised learning
- Responsible AI (explainability, uncertainty)
- Transfer learning and few-shot learning
- Transformers and attention for time series
- Graph neural networks and anomaly detection
- Reservoir computing, spiking neural networks, and representation learning
This year’s edition focuses on four specific areas:
- A) Generative models for time series
- B) Self-supervised learning
- C) Responsible AI for time series
- D) Foundation models trained on large-scale, multimodal data
By addressing these areas, we aim to foster the development of scalable, trustworthy, and generalizable models that reflect current challenges in modern AI.
Organization
Organizers
- Massimiliano Ruocco (NTNU/Sintef, Norway)
- Erlend Aune (HANCE/NTNU, Norway)
- Claudio Gallicchio (University of Pisa, Italy)
- Krzysztof Kotowski (KP Labs, Poland)
- Vincenzo Lomonaco (University of Pisa, Italy)
- Gabriele De Canio (European Space Agency, Germany)
Program Committee
- Sara Malacarne (Research Scientist, Telenor Research)
- Pierluigi Salvo Rossi (Full Professor, NTNU)
- Murad Abdulmajid (Researcher, Sintef DIGITAL)
- Michail Spitieris (Researcher, Sintef DIGITAL)
- Jo Eidsvik (Full Professor, NTNU)
- Emil Stoltenberg (BI)
- Leif Anders Thorsrud (Professor, BI)
- Gard Spreeman (Research Scientist, Sintef)
- Pablo Ortiz (Senior Research Scientist, Telenor Research)
- Vegard Larsen (Researcher, BI/Norges Bank)
- Juan-Pablo Ortega (Full Professor, Nanyang Technological University, Singapore)
- Azarakhsh Jalalvand (Researcher, Ghent University-imec, Belgium and Princeton University, USA)
- Benjamin Paaßen (Researcher, Institute for Informatics, Humboldt-University of Berlin, Germany)
- Petia Koprinkova-Hristova (Full professor, Institute of Information and Communication Technologies, Bulgarian Academy of Sciences)
- Andrea Ceni (Researcher, University of Pisa, Italy)
- Bogdan Ruszczak (Assistant Professor at Opole University of Technology, Research Scientist at KP Labs, Poland)
- Jakub Nalepa (Associate Professor at Silesian University of Technology, Head of AI at KP Labs, Poland)