Special Issue

Info

Machine Learning Journal special issue on Learning from Multi-Label Data

Call For Papers

Traditional supervised classification works under a single-target scenario, i.e. each example (data object) is associated with one single nominal target variable characterizing its property. However, an increasing number of practical applications, such as the (semi)automated annotation of large collections of image/video, music, text, web and biology objects, drug discovery, query categorization, medical diagnosis, tag recommendation and direct marketing, involve data with multiple binary target variables, called multi-label data. The ever-increasing interest on learning from multi-label data (i.e. multi-label learning) is witnessed by the significant amount of work in terms of learning theories, novel algorithms and new applications. Despite this encouraging progress, there are still many open issues to be addressed in this emerging learning scenario. The purpose of this special issue is to solicit recent innovative and promising research findings on multi-label learning. Topics of interest include, but are not limited to:

• Theoretical analysis of multi-label learning
• Novel methodologies/algorithms to learn from multi-label data
• Scalable multi-label learning (presence of large number of labels)
• Learning and/or exploiting label structure (constraints, hierarchies, ontologies)
• Learning from data with multiple non-binary target variables (nominal, real-valued, mixed)
• Evaluation of multi-label learning
• New applications of multi-label learning
• Related learning tasks
  • Feature selection from multi-label data
  • Multi-instance multi-label learning (MIML)
  • Active multi-label learning
  • Semi-supervised multi-label learning

Submissions are expected to represent high-quality, significant contributions in the area of machine learning theories, algorithms, and/or applications. Authors should prepare their manuscripts in accordance with standard Machine Learning formatting guidelines.

Administrative notes

• Authors retain the copyrights to their papers. (See publication agreement on the MLJ website).
• Submissions and reviewing will be handled electronically using standard procedures for Machine Learning. Authors must register with the system before they can submit their manuscripts. Authors must select the appropriate Article Type -- Learning from Multi-Label Data -- when submitting their manuscripts.
• Accepted papers will be published electronically and citable immediately (before the print version appears).

Tentative Schedule

• Submission Deadline: September 30, 2010
• Decisions Announced: February 15, 2011
• Camera-Ready Due: April 30, 2011
• Print Publication: to be announced

Guest Editors

Grigorios Tsoumakas, Lecturer
Department of Informatics, Aristotle University of Thessaloniki
Url: http://mlkd.csd.auth.gr/greg.html
E-mail: greg@csd.auth.gr

Min-Ling Zhang, Associate Professor
School of Computer Science and Engineering, Southeast University
Url: http://cse.seu.edu.cn/people/zhangml/
E-mail: zhangml@seu.edu.cn

Zhi-Hua Zhou, Professor
National Key Laboratory for Novel Software Technology, Nanjing University
Url: http://cs.nju.edu.cn/zhouzh/
E-mail: zhouzh@nju.edu.cn