ICML 2021 Style & Author Instructions
Submitted papers can be up to eight pages long, not including references, plus unlimited space for references. The use of 10-point Times font is mandatory. Any paper exceeding this length will be automatically rejected.
Authors have the option of submitting one supplementary manuscript containing further details of their work and a separate file containing code that supports experimental findings; it is entirely up to the reviewers to decide whether they wish to consult this additional material.
To foster reproducibility, we highly encourage authors to submit code. Reproducibility of results and easy availability of code will be taken into account in the decision-making process.
All submissions must be electronic, anonymized and must closely follow the formatting guidelines in the templates; otherwise they will automatically be rejected.
Previously published papers with substantial overlap written by the authors must be cited in such a way so as to preserve author anonymity. Differences relative to these earlier papers must be explained in the text of the submission. For example, (This work develops [our earlier work], which showed that).
Reviewing for ICML 2021 is double-blind; i.e., reviewers will not know the authors’ identity (and vice versa). Detailed instructions for how to ensure your anonymity are also contained in the above example paper. In brief, please refer to your prior work in the third person wherever possible, and please refrain from adding acknowledgements, grant numbers as well as public github repository links to your submitted paper. If you need to make an anonymous reference (e.g., if you refer to your own work that is under review elsewhere), please upload this work as supplementary material (see below). Note that anonymizing your paper is obligatory, and papers that explicitly or implicitly reveal the authors’ identities may be rejected. A reviewer may be able to deduce the authors’ identities by using external resources, such as technical reports published on the web. The availability of information on the web that may allow reviewers to infer the authors’ identities does not constitute a breach of the double-blind submission policy.
ICML 2021 supports the submission of two kinds of supplementary material -- supplementary manuscripts and code/data -- which can be used to provide additional evidence. In particular, if you make anonymous references in the paper, please upload the referenced papers, so that the reviewers can take a quick look. Please also take care not to reveal your identity in the supplementary material.
For code submission, we expect authors to put in reasonable effort to anonymize the submitted code and institution. This means that author names and licenses should be removed. Submission of code through anonymous github repositories is allowed; however, they have to be on a branch that will not be modified after the submission deadline. Please enter the github link in a standalone text file in a submitted zip file. Finally, we understand that many of our authors work with highly sensitive datasets, and are not asking for private data submission.
Note that submitted papers must be entirely self-contained. Reviewers are encouraged, but not obliged to look at the provided supplementary material because we also do not want to burden reviewers unnecessarily. In particular, you must not use supplementary material for extending the length of your paper. If there is material that you believe is critical to the evaluation of your paper, it needs to be included in the paper.
The supplementary material could be submitted as either a zip file or a pdf.
Supplementary material will not be published or archived, and there are no format restrictions. If you want to include it in a final version of the paper, you must put it on a web site and reference the site in the final version of your paper.
ICML uses the Toronto Paper Matching System (TPMS) and OpenReview in order to assign submissions to reviewers and area chairs. Both software packages compute similarity scores between ICML submissions and reviewers’ papers. During the submission process, you will be asked to agree to the use of TPMS and OpenReview for your submission. (Note that OpenReview is used only for matching; your paper will not be made public.)
Dual Submission Policy
It is not appropriate to submit papers that are substantially similar (or identical) in contents to versions that have been previously published, or accepted for publication, or which are under review to other peer reviewed conferences or journals at any time while they are also under consideration for ICML. Such submissions violate our dual submission policy and will be rejected.
Submission is permitted for papers presented or to be presented at conferences or workshops without proceedings (e.g., ICML or NeurIPS workshops), or with only abstracts published.
Submission is permitted for papers that have previously been made available as a technical report (or similar, e.g., in arXiv). In this case we suggest the authors not cite the report, so as to preserve anonymity.
Finally, note that previously published papers with substantial overlap written by the authors must be discussed and cited in such a way so as to preserve author anonymity. Differences relative to these earlier papers must be explained in the text of the submission. For example, (This work develops [our earlier work], which showed that).
From March 21 to 27, authors can see the reviews and respond to their content.
Your response will be used by the Program Committee in their judgment of the paper, so it is in your advantage to respond. The maximum length of the response is 5000 character or, alternatively, a 1 page .pdf with fonts no smaller than 10pt.
Authors can submit one response per submission. Once author feedback is enabled, authors will see a link to “Author Feedback” from the author console. Any of the authors of a paper can enter/edit the response, and the response can be returned to and edited up to the deadline for author feedback.
Remember that reviewing is double-blind. Do not include any information in the response that can identify you or your co-authors. Please do not include any URLs in your response.
We recommend using your judgement when crafting a response. There is no need to respond to every minor question or suggestion for improvement. Rather, the response is a good opportunity for addressing issues like a reviewer’s uncertainty about a point, a reviewer making an incorrect assumption, or a reviewer misunderstanding a part of the paper. We recommend being polite and professional.
Code of Conduct
Authors will be asked to confirm that their submissions accord with the ICML code of conduct.