Machine learning is grappling with a fundamental challenge: bias. It appears in many forms — class imbalance, spurious correlations, algorithmic unfairness, and dataset shift — and is often tackled in isolation.

This workshop breaks down those silos. We are bringing together researchers from the fairness, robustness, and generalisation communities to build a unified theoretical framework for understanding and mitigating learning biases.

In this event, we will dig into the technical challenges, foster interdisciplinary dialogue, and promote collaborative problem-solving. Whether you're a seasoned professor, an industry researcher, or a PhD student, if you're working on making ML safer, more reliable, and more efficient, this workshop is for you.

Goals

• Advancing theoretical understanding of how diverse data imbalances shape learning.

• Fostering interdisciplinary dialogue among researchers in fairness, robustness, and dataset shift to build a common vocabulary.

• Promoting principled approaches over narrow heuristics.

• Emphasising data distributions as the central unifying factor behind ML pathologies.

Program (tentative)

• 8:30 AM – Registration & Coffee

• 8:45 AM – Opening Remarks

• 9:00 AM – Levent Sagun

• 9:45 AM – Aasa Feragen

• 10:30 AM – Break & Poster Session

• 11:15 AM – Fanny Yang

• 12:00 PM – Emanuele Francazi

• 12:45 PM – Lunch Break

• 2:00 PM – Invited Talk TBD

• 2:45 PM – Contributed Talk (Best Paper)

• 3:30 PM – Contributed Talk (Best Paper)

• 4:15 PM – Poster Session

Confirmed Speakers

…with more to be announced!

Call for papers

We invite researchers to submit papers exploring the themes of our workshop, with a special focus on contributions that promote a unified understanding of learning biases. We are excited to receive interdisciplinary work and theoretical papers that draw connections between different subfields of machine learning and explore these connections, aiming to address fundamental questions, such as:

• Under which conditions are different mechanisms that resemble class imbalance quantitatively equivalent? 

• Can different sources of bias be controlled in such a way that they mitigate one another?  

• How can a unified understanding of these biases lead to the development of more intrinsically fair and robust machine learning systems?

Workshop Themes

The scope of the workshop includes, but is not limited to, the following themes:

• Class and subpopulation imbalance 

• Spurious correlations and shortcut learning 

• Dataset shift and out-of-distribution generalisation 

• Algorithmic bias and fairness in machine learning 

• Biases emerging from model initialisation or architectural design 

Submission Guidelines

Submissions can be either regular papers (up to 5 pages) or tiny papers (up to 2 pages). All accepted papers will be presented during our poster sessions, and a select few will be chosen for short oral presentations.

Submissions will be managed through OpenReview. The link will be provided here shortly.

Important Dates

Here are the key deadlines for the workshop. Please note all deadlines are Anywhere on Earth (AoE).

• Paper Submission Open: September 15, 2025

• Paper Submission Deadline: October 10, 2025

• Paper Acceptance Notification: October 31, 2025

Organisers