Workshop on Spurious Correlation and Shortcut Learning: Foundations and Solutions

Workshop at The International Conference on Learning Representations (ICLR) 2025

Reliance on spurious correlations due to simplicity bias is a well-known pitfall of deep learning models. This issue stems from the statistical nature of deep learning algorithms and their inductive biases at all stages, including data preprocessing, architectures, and optimization. Therefore, spurious correlations and shortcut learning are fundamental and common practical problems across all branches of AI. The foundational nature and widespread occurrence of reliance on spurious correlations and shortcut learning make it an important research topic and a gateway to understanding how deep models learn patterns and the underlying mechanisms responsible for their effectiveness and generalization. This workshop aims to address two aspects of this phenomenon: its foundations and potential solutions.

Submission Deadline: 10th February 2025, 11:59 PM (AoE).
The workshop will be held on 27 or 28th April, 2025 in Singapore EXPO.
For latest news about the workshop, follow @scslworkshop on X/Twitter.


Keynote Speakers

Pavel Izmailov

NYU / Anthropic

Baharan Mirzasoleiman

UCLA

David Krueger

University of Montreal

Katherine Hermann

Google DeepMind

Stefano Sarao Mannelli

Chalmers University of Technology

Panelists

Soheil Feizi

UMD

Andrew Gordon Wilson

NYU

Please submit questions for our panelists here.

Organizers

Hesam Asadollahzadeh

Sharif University of Technology

Polina Kirichenko

NYU / Meta (FAIR) / Princeton

Mahdi Ghaznavi

Sharif University of Technology

Mahdieh Soleymani Baghshah

Sharif University of Technology

Mohammad Hossein Rohban

Sharif University of Technology

Parsa Hosseini

UMD

Aahlad Puli

NYU

Arash Marioriyad

Sharif University of Technology

Shikai Qiu

NYU

Nahal Mirzaie

Sharif University of Technology


Questions?

Contact us at scslworkshop@gmail.com or @scslworkshop.