Call for papers

Machine learning has achieved considerable successes in recent years, but these successes crucially rely on human machine learning experts, who select appropriate ML architectures (deep learning architectures or more traditional ML workflows) and their hyperparameters. As the complexity of these tasks is often beyond non-experts, the rapid growth of machine learning applications has created a demand for off-the-shelf machine learning methods that can be used easily and without expert knowledge. We call the resulting research area that targets progressive automation of machine learning AutoML.

AutoML aims to automate many different stages of the machine learning process such as:

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

  • Meta learning and transfer learning

  • Representation learning and automatic feature extraction / construction

  • Demonstrations (demos) of working AutoML systems

  • Automatic generation of workflows / workflow reuse

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

  • Automatic feature transformation to match algorithm requirements

  • Automatic detection and handling of skewed data and/or missing values

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

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

  • Automatic selection of evaluation metrics / validation procedures

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

  • User interfaces for AutoML

  • Automatic leakage detection

  • Automatic inference and differentiation

We especially encourage demos of working AutoML systems; demo proposals are submitted through an accompanying paper. We also encourage the participants of the AutoML challenge (http://automl.chalearn.org/) to submit a paper.

The best 2-3 papers will be invited for oral plenary presentation. All other accepted papers will be presented as posters and short poster spotlight presentations. Unless otherwise indicated, we will list all accepted papers on this website as the workshop's online proceedings. For submission details please see the submission page.

Important Dates:

  • Early submission deadline: June 12, 2017, UTC-12 (anywhere in the world)

  • Notification of acceptance: June 21, 2017

For authors who don't need the acceptance notice early, we have a 2nd "late breaking paper" submission cycle. The only difference between this and the first submission is in the dates of submission and acceptance notification. Note that rejects from the first deadline will not be eligible for resubmission.

  • 2nd submission deadline: July 17, 2017, UTC-12 (anywhere in the world)

  • Notification of acceptance: July 28, 2017

Student support:

We are happy to be able to provide two free *full* registrations to ICML for student presenters (oral or poster). We will contact all authors of accepted papers and select two students based on need and merit (quality of the submission).