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: 16th February 2025, 11:59 PM (AoE).
The workshop will be held on 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

Program Committee

  • Ali Abdollahi, Sharif University of Technology
  • Hesam Asadollahzadeh, Sharif University of Technology
  • Mohammad Azizmalayeri, Amsterdam UMC
  • Mahdieh Soleymani Baghshah, Sharif University of Technology
  • Samuel Bell, Meta FAIR
  • Yize CHENG, University of Maryland, College Park
  • Yongqiang Chen, MBZUAI & CMU
  • Allison Chen, Princeton University
  • Alireza Dehghanpour Farashah, McGill University
  • Anastasiia Fadeeva, Google DeepMind
  • Mohamadreza Fereydooni, Sharif University of Technology
  • Rameshwar Garg, Columbia University
  • Mahdi Ghaznavi, Sharif University of Technology
  • Shantanu Ghosh, Boston University
  • Fahimeh Hosseini Noohdani, Sharif University of Technology
  • Amirmohammad Izadi, Sharif University of Technology
  • Polina Kirichenko, Princeton University
  • Jack Lanchantin, Meta
  • Tyler LaBonte, Georgia Tech
  • Jie S. Li, University of Maryland, College Park
  • Daohan Lu, New York University
  • Alexander Lyzhov, New York University
  • Divyat Mahajan, Mila, Université de Montréal
  • Arash Marioriyad, Sharif University of Technology
  • Martin Marek, New York University
  • Viacheslav Meshchaninov, Higher School of Economics
  • Faridoun Mehri, Sharif University of Technology
  • Nahal Mirzaie, Sharif University of Technology
  • David Yu Miller, University of Maryland, College Park
  • Mazda Moayeri, Meta
  • Mohammad Mozafari, Sharif University of Technology
  • Nihal Murali, University of Pittsburgh
  • Amir Najafi, Sharif University of Technology
  • Sumit Nawathe, University of Maryland, College Park
  • Dang Nguyen, UCLA
  • Hosna Oyarhoseini, Sharif University of Technology
  • Indu Panigrahi, Princeton University
  • Xiang Pan, New York University
  • Mohammad Pezeshki, Meta
  • Aahlad Manas Puli, New York University
  • GuanWen Qiu, University of Pennsylvania
  • Saksham Rastogi, Indian Institute of Science
  • Yi Ren, University of British Columbia
  • Mohammad Hossein Rohban, Sharif University of Technology
  • Mahdi Salmani, University of Southern California
  • Mahdi Samiei, Sharif University of Technology
  • Soroush Vafaie Tabar, Sharif University of Technology
  • Aryan Yazdan Parast, University of Melbourne
  • Guangtao Zheng, University of Virginia
  • Yin Zhou, Columbia University
  • Tyler Zhu, Princeton University


Questions?

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