Call for papers

Important Dates

  • Submission system opens: April 1st 2020 (https://easychair.org/conferences/?conf=automl2020)
  • Submission deadline: April 23rd 2020 (Anywhere on earth) May 20th 2020 (Anywhere on earth)
  • Author notification: May 25th 2020 June 17th
  • Camera ready copy due: July 9th
  • Workshop day: 18th 2020

Remark on COVID-19:

Due to COVID-19 the workshop will be completely virtual. All keynote talks and contributed talks will be streamed and followed by a live Q&A session. Each accepted paper has a one-minute spotlight presentation which will be streamed, too. In additional, there will be a Zoom session for each accepted paper during one of the two poster sessions to ask questions to the authors and discuss their work. The final panel discussion will also be streamed live.

We will post links to the individual events on the day of the workshop.

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 http://icml2020.automl.org/. There will be no archival proceedings. For submission details see Submission.