Call for papers

Important Dates

Workshop Format

Due to COVID-19 the workshop will be completely virtual. We will update details of the format shortly.

We invite submissions on the topics of:

  • Model selection, hyper-parameter optimization, and model search

  • Neural architecture search

  • Meta-learning and transfer learning

  • Bayesian optimization for AutoML

  • Evolutionary algorithms for AutoML

  • Multi-fidelity optimization

  • Predictive models of performance

  • Automatic feature extraction / construction

  • Automatic data cleaning

  • Automatic generation of workflows / workflow reuse

  • Automatic problem "ingestion" (from raw data and miscellaneous formats)

  • Automatic feature transformation to match algorithm requirements

  • Automatic acquisition of new data (active learning, experimental design)

  • Automatic report generation (providing insight on automatic data analysis)

  • Automatic selection of evaluation metrics / validation procedures

  • Automatic selection of algorithms under time/space/power constraints

  • Automatic construction of fair and unbiased machine learning models

  • Automation of semi-supervised and unsupervised machine learning

  • Demos of existing AutoML systems

  • Robustness of AutoML systems (w.r.t. Randomized algorithms, data, hardware etc.)

  • Human-in-the-loop approaches for AutoML

  • Learning to learn new algorithms and strategies

  • Hyperparameter agnostic algorithms

Submission Format

We welcome submissions up to 6 pages in JMLR Workshop and Proceedings format (plus 10 pages for references and appendix). All accepted papers will be presented as posters. We will invite the 2-3 best papers for an oral plenary presentation. Unless indicated by the authors, we will provide PDFs of all accepted papers on There will be no archival proceedings. For submission details see Submission.

We are using OpenReview to manage submissions. Shortly after the author notification, the de-anonymized paper and anonymous reviews of all accepted papers and opt-in rejected papers will become public in OpenReview, and open for non-anonymous public commenting. Authors of rejected papers will have until July 1, 2021 to opt in to make their de-anonymized papers (including anonymous reviews) public in OpenReview. Otherwise, there will be no public record that the rejected paper was submitted.


We ask that authors think about the broader impact and ethical considerations of their work. For example, authors may consider whether there is potential use for the data or methods to create or exacerbate unfair bias. Authors are not required to have a broader impact statement in their paper, but will be asked to submit one paragraph (3-4 sentences) as a separate field in OpenReview at the time of submission. See this guide for help with the statement. Reviewers will be asked to consult the ICLR 2021 code of ethics when reviewing submissions. Reviewers cannot reject papers based on ethical considerations, but in very rare cases, the workshop organizers may reject papers that blatantly violate the code of ethics (e.g., if the primary application directly causes harm or injury).