About ICLR

The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning.

ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.

 

Key dates

The planned dates are as follow:

      • Abstract submission: Sept 21 (Anywhere on Earth)

      • Submission date: Sept 28 (Anywhere on Earth)

      • Reviews released: Nov 4

      • Final decisions: Jan 20

 

Subject Areas

We consider a broad range of subject areas including feature learning, metric learning, compositional modeling, structured prediction, reinforcement learning, and issues regarding large-scale learning and non-convex optimization, as well as applications in vision, speech recognition, text understanding, robotics, health care, sustainability, music, games, computational biology, and others.

A non-exhaustive list of relevant topics:

      • unsupervised, semi-supervised, and supervised representation learning

      • representation learning for planning and reinforcement learning

      • representation learning for computer vision and natural language processing

      • metric learning and kernel learning

      • sparse coding and dimensionality expansion

      • hierarchical models

      • optimization for representation learning

      • learning representations of outputs or states

      • Optimal transport

      • theoretical issues in deep learning

      • visualization or interpretation of learned representations

      • implementation issues, parallelization, software platforms, hardware

      • applications in audio, speech, robotics, neuroscience, computational biology, or any other field

      • societal considerations of representation learning including fairness, safety, privacy, and interpretability

​

Double blind reviewing

Submissions will be double blind: reviewers cannot see author names when conducting reviews, and authors cannot see reviewer names. We use OpenReview to host papers and allow for public discussions that can be seen by all, comments that are posted by reviewers will remain anonymous. The program will include keynote presentations from invited speakers, oral presentations, and posters.

Authors can revise their paper as many times as needed up to the paper submission deadline. Changes to the paper will not be allowed while the paper is being reviewed. During the discussion phase (between area chairs, reviewers and authors), edits will again be allowed; a pdfdiff will be done against the submission at the paper submission deadline. Area chairs and reviewers reserve the right to ignore changes that are significant from the original scope of the paper. As in the past three years, workshops will have their own organisation and call for contributions.

 

Submission Instructions

This year we are asking authors to submit paper abstracts by the abstract submission deadline of Sept 21, 2022. Please note that no changes on the authors and their orders can be made after the abstract submission deadline. Also please make sure that all authors have an OpenReview profile with the latest information.  Abstracts submitted by the abstract submission deadline must be genuine, placeholder or duplicate abstracts will be removed.

The full paper submission deadline is Sept 28, 2022. Abstracts and papers must be submitted using the conference submission system at: https://openreview.net/group?id=ICLR.cc/2023/Conference. The submission site will be open on Aug 22, 2022.  

Paper length

• There will be a strict upper limit of 9 pages for the main text of the initial submission, with unlimited additional pages for citations.
• Authors may use as many pages of appendices (after the bibliography) as they wish, but reviewers are not required to read these.

 

Style files and Templates

To prepare your submission to ICLR 2023, please use the LaTeX style files provided at:

https://github.com/ICLR/Master-Template/raw/master/iclr2023.zip

 

Authors are strongly encouraged to participate in the public discussion of their paper, as well as of any other paper submitted to the conference. Submissions and reviews are both anonymous. For detailed instructions about the format of the paper, please visit www.iclr.cc.

 

More information about ICLR 2023 is available at:  https://iclr.cc/Conferences/2023