Machine Learning for Irregular Time Series (ML4ITS2026): Advances in Generative Models, Global Models and Self-Supervised Learning

Machine Learning for Irregular Time Series (ML4ITS) is a vital research area addressing real-world challenges in finance, healthcare, and environmental science where data exhibits irregular sampling, missing values, noise, and multiresolution characteristics. This workshop brings together researchers to advance state-of-the-art techniques for handling scarce data, limited labels, and uncertainty quantification in time series modeling.

We invite submissions on:

• Generative models (GANs, diffusion, masked modeling)
• Self-supervised and unsupervised learning
• Responsible AI (explainability, uncertainty)
• Transfer learning and few-shot learning
• Transformers, attention mechanisms, and graph neural networks
• Anomaly detection and foundation models

This year's focus areas: Generative models for time series, Self-supervised learning, Responsible AI, and Foundation models trained on large-scale multimodal data.

The workshop also features a Special Session on Time Series for Space Applications. Learn more in the Time Series for Space Applications section.

Machine learning is vital for autonomous space operations. Spacecraft telemetry presents unique challenges with irregular sampling, missing data, and complex dependencies. Two curated datasets have been released by ESA, Airbus Defence and Space, and KP Labs:

• ESA-ADB: Article, Dataset, Code
• OPSSAT-AD: Article, Dataset, Code

Topics: Time series modeling for telemetry, anomaly detection, forecasting, onboard ML, data compression, and explainable models for space. Cross-domain applications include finance, robotics, IoT, and healthcare.

Papers must be written in English and formatted according to the Springer LNCS guidelines followed by the main conference. Submissions should be made through the workshop's CMT submission page. After logging in, create a new submission in your author console, and select the track on "ML4ITS2026". Regular and short papers presenting work completed or in progress are invited.

• Regular papers are expected to provide original and innovative contributions. Max length: 14 pages including references.
• Short papers, describing innovative ongoing research showing relevant preliminary results, are maximum 6 pages.
• We also allow presentation only contributions (no page restrictions, not included in proceedings), which may include work already published elsewhere or ongoing research that is relevant and may solicit fruitful discussion at the workshop.

Papers authors will have the faculty to opt-in or opt-out for publication of their submitted papers in the joint post-workshop proceedings published by Springer Communications in Computer and Information Science, organised by focused scope and possibly indexed by WOS. Notice that novelty is not essential for contributed papers that will not appear in the workshop proceedings, as we invite papers that have already been presented or published elsewhere with the aim of maximizing the dissemination and cross-pollination of ideas among the topic of the workshop.

At least one author of each accepted paper must have a full registration and be in-person to present the paper. Papers without a full registration or in-presence presentation won't be included in the post-workshop Springer proceedings.

The following deadlines are in AoE time zone (UTC – 12).

• Paper submission deadline: June 5, 2026 June 12, 2026
• Acceptance notification: July 12, 2026 July 20, 2026
• Camera Ready: July 20, 2026 September 20, 2026
• Workshop date: September 11, 2026