Call for papers
Although this workshop will be taking place at the International Conference for Machine Learning, we are eager to hear from researchers inside and outside of computer science. “Causal inference” and theorizing about causation encompasses a wide range of researchers and a variety of disciplines, including economics, sociology, political science, epidemiology, biostatistics, medicine, and philosophy. Contributions from scholars focusing on theoretical, methodological, or applied questions pertaining to causation are extremely welcome.
We invite contributions on the following topics (not exclusively):
What are justifiable assumptions in specific domains and, if different from "standard assumptions", can we formalize them to aid causal inference?
How can we foster the communication of domain-specific assumptions between domain experts and machine learners?
What are the dangers of modeling causal relationships between social constructs?
Are we applying causal language too broadly? In which domains does causal modeling make sense conceptually?
What are the roles of human expertise vs. machine learning in causal research?
(When) can we meaningfully relax the standard assumptions of causal inference while retaining the ability to (partially) answer causal queries?
Can we continually trade-off the austerity of assumptions with the sharpness of partial identification bounds?
(When) can we simply accessorize our machine learning-based predictions with causal assumptions (e.g., no unmeasured confounding) or statistical concepts (e.g., bootstrapping) after the fact?
How can we avoid inferential errors (e.g., overfitting) due to neglected causal models?
What is required to support untestable assumptions in practical applications? How badly can things go wrong?
Contributions on other topics are also very welcome.
Since we aim to attract contributions from various disciplines, we invite contributions of the following forms.
Ongoing research paper and position pieces: A 4-6 page research paper about ongoing work that has not yet been published in a venue with proceedings. While we welcome unfinished work, submissions in this track should contain original ideas, connections, or results. The main body of the submission (including most important figures and tables) must not exceed 6 pages with unlimited additional space for references and supplementary material. Reviewers will be asked to judge the main body of the paper and will not be required to read the supplementary material.
Extended abstracts: We recognize that a 4-6 page research paper submission may not be standard across disciplines. Therefore, we will also accept submissions in the form of extended abstract proposals of 750-1000 words + 1 Figure or Table. The abstract can be tied to an existing longer work-in-progress that does not meet the 4-6 page criteria or can be work specially tailored to this workshop. If you are at all unsure about whether your submission meets these criteria, please feel free to reach out to Lily Hu or Laura Balzer.
All submissions will be peer-reviewed. A subset will be invited for a contributed talks, and the remaining will be invited to present at the poster sessions. This workshop is non-archival.
The aim of this workshop is to facilitate interdisciplinary dialogue on and engage theoretical and methodological challenges to studying causation and causal inference. To this end, it is our priority to make the workshop’s format and contents reflective of and amenable to the breadth of scholars working on this important topic.
Important dates
Submission deadline: June 18, 2021 (AoE)
Author notification: July 2, 2021, July 9, 2021 (We apologize for the delay.)
Camera-ready submission: TBA
Workshop: July 23, 2021
Formatting and submission instructions
Please submit your work as a single pdf on CMT:
Please use the following LaTeX template files for all submissions: