Call For Papers

The conference calls for high-quality, original research papers in the theory and practice of machine learning. The conference also solicits proposals focusing on frontier research, new ideas and paradigms in machine learning. We encourage submissions from all parts of the world, not only confined to the Asia-Pacific region.

Submission

This year we are running two publication tracks: Authors may submit either to the conference track, for which the proceedings will be published as a volume of Proceedings of Machine Learning Research (PMLR) series, or to the journal track for which accepted papers will appear in a special issue of the Springer journal Machine Learning.

Please note that submission arrangements for the two tracks are different.

Conference Track

For the conference track please submit your manuscript via CMT at:

https://cmt3.research.microsoft.com/ACML2018 (available until August 1).

Please be aware that ACML runs two submission rounds to the conference track: The first round can result in an Accept, Reject, Reject with Encouragement to Resubmit or Conditional Acceptance (i.e., subject to changes made by the second round) decision. There is no author rebuttal phase in this round. The second round has the more usual Accept or Reject outcomes and does include an author rebuttal phase.

Manuscripts must be written in English, be a maximum of 16 pages (including references, appendices etc.) and follow the PMLR style. If required supplementary material may be submitted as a separate file, but reviewers are not obligated to consider this, and your manuscript should therefore stand on its own merits without any supplementary material.

Papers will be published in a dedicated volume of the PMLR series.

You can download a suitable Latex template and style file from here.

Submissions must have all detail identifying the author(s) removed from the original manuscript.

Submissions that are overlength, not in the correct format, or contain clear identifying detail - for example the authors' names below the title - will be rejected without review.

Journal Track

In addition to the Conference Track, the Asian Conference on Machine Learning will be running a Journal Track. In order to ensure an efficient reviewing process, we encourage submissions of papers up to 20 pages. The journal track will follow the reviewing process of the Machine Learning journal. This includes allowing papers that require minor changes to be resubmitted after a first round review. The Journal Track committee will aim to complete the reviewing process in time for this year’s conference. In the unlikely event that the reviewing process for a paper could not be completed in time (for this year’s conference), the paper will not be considered for the conference and the review will be completed as a regular submission to the Machine Learning journal. Two submission deadlines are available for submitting journal track manuscripts.

For the journal track, please submit via Springer's Editorial Manager system at:

https://www.editorialmanager.com/mach (available until March 31 available until April 20).

Log in as Author, click on Submit New Manuscript, and select S.I.: ACML 2018 from the Choose Article Type drop-down list. Papers will be published in a special issue of Machine Learning. Manuscripts must be written in English; please follow the instructions for authors at:

http://www.springer.com/computer/ai/journal/10994

There is no specific page limit for journal submissions, however papers accepted to the journal track must still be presented at the conference in order to be published, therefore it must be possible to describe at least the major parts of your submission in a talk of around 20 minutes duration. Extended version of published conference paper is not eligible for journal track submission.

Important dates

Deadlines are 23:59 Pacific Standard Time (PST)

Topics

Topics of interest include but are not limited to:

1. Learning problems

• Active learning
• Bayesian machine learning
• Deep learning, latent variable models
• Dimensionality reduction
• Feature selection
• Graphical models
• Learning for big data
• Learning in graphs
• Multiple instance learning
• Multi-objective learning
• Multi-task learning
• Semi-supervised learning
• Sparse learning
• Structured output learning
• Supervised learning
• Online learning
• Transfer learning
• Unsupervised learning

2. Analysis of learning systems

• Computational learning theory
• Experimental evaluation
• Knowledge refinement
• Reproducible research
• Statistical learning theory

3. Applications

• Bioinformatics
• Biomedical information
• Collaborative filtering
• Healthcare
• Computer vision
• Human activity recognition
• Information retrieval
• Natural language processing
• Social networks
• Web search

4. Learning in knowledge-intensive systems

• Knowledge refinement and theory revision
• Multi-strategy learning
• Other systems