About

Advanced Artificial Intelligence (AI) techniques based on deep representations, such as GPT and Stable Diffusion, have demonstrated exceptional capabilities in analyzing vast amounts of data and generating coherent responses from unstructured data. They achieve this through sophisticated architectures that capture subtle relationships and dependencies. However, these models predominantly identify dependencies rather than establishing and making use of causal relationships. This can lead to potential spurious correlations and algorithmic bias, limiting the models’ interpretability and trustworthiness. In contrast, traditional causal discovery methods aim to identify causal relationships within observed data in an unsupervised manner. While these methods show promising results in scenarios with fully observed data, they struggle to handle complex real-world situations where causal effects occur in latent spaces when handling images, videos, and possibly text.

Recently, causal representation learning (CRL) has made significant progress in addressing the aforementioned challenges, demonstrating great potential in understanding the causal relationships underlying observed data. These techniques are expected to enable researchers to identify latent causal variables and discern the relationships among them, which provides an efficient way to disentangle representations and enhance the reliability and interpretability of models. The goal of this workshop is to explore the challenges and opportunities in this field, discuss recent progress, and identify open questions, and provide a platform to inpire cross-disciplinary collaborations. This workshop will cover both theoretical and applied aspects of CRL, including, but not limited to, the following topics:

Tentative Invited Speakers (Ranked by the last name)

Frederick Eberhardt

Frederick Eberhardt
California Institute of Technology

Arthur Gretton

Arthur Gretton
Gatsby Computational Neuroscience Unit / UCL / Google Deepmind

James M. Robins (tentative)

James M. Robins (tentative)
Harvard University

Yan Liu

Yan Liu
University of Southern California

Thomas Richardson (tentative)

Thomas Richardson (tentative)
University of Washington

Bernhard Schölkopf

Bernhard Schölkopf
Max Planck Institute for Intelligent Systems

Cheng Zhang

Cheng Zhang
Microsoft Research

Tentative Panelists (Ranked by the last name)

Mingming Gong

Mingming Gong
University of Melbourne / MBZUAI

Emre Kıcıman

Emre Kıcıman
Microsoft Research

Jing Ma

Jing Ma
Case Western Reserve University

Ricardo Silva

Ricardo Silva
Department of Statistical Science, UCL / Gatsby Computational Neuroscience

Mihaela van der Schaar

Mihaela van der Schaar
University of Cambridge

Tentative Schedule

Important Dates (Anywhere on Earth,TBD)

Organizers:

Guangyi Chen

Guangyi Chen
Carnegie Mellon University / MBZUAI

Haoxuan Li

Haoxuan Li
Peking University

Sara Magliacane

Sara Magliacane
University of Amsterdam

Zhijing Jin

Zhijing Jin
Max Planck Institute / ETH

Biwei Huang

Biwei Huang
UC San Diego

Francesco Locatello

Francesco Locatello
Institute of Science and Technology Austria

Peter Spirtes

Peter Spirtes
Carnegie Mellon University

Kun Zhang

Kun Zhang
Carnegie Mellon University / MBZUAI

For any question, please contact thecrlcommunity@gmail.com.