Special Session on
“Emerging Multi-label Learning Classifiers”

Aim and Scope

Research on multi-label learning has received increasing attention mainly because many real-world problems can be modeled under this learning paradigm. Several researchers are developing approaches for feature; and instance selection, the correction of the imbalance between labels, noise detection, and the reduction of feature and label spaces, to the adaptation of algorithms to directly handling the multi-label data, the combination of supervised and semi-supervised approaches for constructing better classifiers, the development of methods for extreme multi-label classification, deep models, and so on. Multi-label learning is an exciting area that involves a set of challenges and difficulties that usually do not appear in other learning paradigms, such as the automatic modeling of inter-label correlations, treating the imbalance between labels, and the infeasibility of using certain approaches to problems with a large number of labels. Graphs are a convenient abstraction to model functional and/or structural dependencies between such entities and find application in fields where the intrinsic nature of the datum is relational. Hence, learning from graphs can be the key towards solving complex problems, and has indeed become a thriving research topic. Therefore, the aim of this special session is to enhance the state-of-the-art in the multi-label learning area both theoretical multi-label learning papers, as well as papers discussing real-world applications involving multi-label data. This special session will provide a platform for researchers working in this area to present their work and interact with each other.

The topics of the special issue include, but are not limited to:

  • Methods for multi-label classification and ranking
  • Evaluation measures and strategies for multi-label data
  • Learning label structure and relationships
  • Embeddings and representations of multi-label data
  • Explainable multi-label learning
  • Trustworthy multi-label learning
  • Extreme multi-label classification
  • Deep multi-label learning
  • Learning from partially labeled data
  • Weak multi-label learning
  • Zero-shot and few shot multi-label learning
  • Semi-supervised learning from multi-label data
  • Active learning from multi-label data
  • Dimensionality reduction (feature selection) of multi-label data
  • Hierarchical multi-label classification and learning
  • Learning from streams of multi-label data
  • Applications in a variety of domains, including life sciences, medicine, engineering, and multimedia

Paper Submission

Potential authors may submit their manuscripts for presentation consideration through ICETCI 2023 submission system electronically at , following the conference guidelines. All submissions will go through peer review process. To submit your paper to this special session, you have to choose our special session title on the submission page.

Important Dates

Paper submission deadline: Mar 08, 2023
Mar 30, 2023
Apr 15, 2023
Paper acceptance notification date: June 05, 2023
Final paper submission and early registration deadline: June 21, 2023


Dr Reshma Rastogi, Associate Professor, South Asian University
Email ID: