Call for Papers

We invite submissions from researchers and practitioners across the spectrum of machine learning, with a particular focus on causal representation learning. This call extends to those applying these models in real-world scenarios across various domains such as healthcare, finance, and transportation. Submissions that explore the integration of causal insights into data-driven models to improve interpretability, reliability, and effectiveness are highly encouraged.

Furthermore, we seek contributions from scholars in the natural sciences (physics, chemistry, biology) and social sciences (including educational sciences and sociology) who utilize these advanced computational models to address complex causal questions within their fields. This interdisciplinary approach aims to foster a deeper understanding and broader applicability of causal representation learning. We welcome submissions related to, but not limited to, the following key areas:

Theoretical Aspects of Causal Representation Learning: Concepts, frameworks, and methodologies that underpin causal inference and representation in machine learning.
Causal Representation Learning Models: Innovative models and algorithms that enhance the ability of AI systems to derive causal relationships from large datasets.
Causal Generative Models: Approaches that utilize generative models to understand and simulate causal processes.
Causal Foundation Models: Exploration of foundation models that incorporate causal reasoning capabilities.
Causal Discovery with Latent Variables: Techniques and tools designed to uncover hidden causal structures in complex datasets.
Causal Representation Learning for Treatment Effect Estimation: Methodologies that leverage causal inference to predict the outcomes of interventions.
Application of Causal Representation Learning in Data Mining and Recommendation Systems: Practical implementations and case studies demonstrating the benefits of causal approaches in various applications.

Submission Instructions

Format and Length:

All submissions must be in PDF format. Each submission is limited to four content pages, including all figures and tables. There is no limit on additional pages containing references and supplementary materials. Please note that reviewers are not required to read the supplementary materials. The camera-ready versions of accepted papers may include up to five content pages. Submissions should adhere to the ICDM 2024 LaTeX style file. Please submit your manuscripts on Open Reivew

Nonarchival:

Our workshop is nonarchival. Accepted papers will be posted on our workshop website but will not be published in conference proceedings, allowing for future submissions to other venues.

Dual-submission Policy:

We welcome ongoing and unpublished work. Submissions may include papers currently under review or those that have been recently accepted to other venues without published proceedings.

Visibility:

The review process is confidential. Submissions and reviews will remain private, and only accepted papers will be made publicly available on the workshop website.

All submissions must be anonymized to adhere to our double-blind reviewing policy. This includes removing any identifying information from the paper and any supplementary or linked material, such as code. If linking to external material, ensure that the links support anonymous browsing. Acknowledgements should be omitted at the submission stage. If you need to cite your own work, do so in a manner that does not compromise the double-blind review process. Submissions that fail to comply with these guidelines will be rejected.

Important Dates:

Workshop Papers Submission: ~~September 10, 2024~~ October 20, 2024
Acceptance Notification: November 7, 2024
Workshop Date: December 9, 2024