Call for papers
Special Session on "MACHINE LEARNING FOR PARTIALLY LABELED DATA"
to be held at the 19th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (IPMU 2022)
Milan (Italy), July 11-15, 2022
Session topic and goal
This session aims to target Machine Learning techniques for dealing with incompletely labeled data. Typically, the most effective Machine Learning systems are those based on training data that are fully labeled. However, obtaining fully labeled
data can be an infeasible task in many fields due to the involved costs or required resources. As a result, recently, increasing interest has been devoted to the development of techniques capable of dealing with incompletely labeled data. Several types of
learning problems have been considered, including semi-supervised learning but also more general forms of weak supervision, and various techniques for solving these problems have been explored over the years, also in terms of novel conceptual frameworks that
aim to shed a light on this topic. Nevertheless, there are still many open problems.
This special session is intended to serve as a common space for researchers in this field to share their latest findings on incompletely labeled data, including the development of practical algorithms to address different tasks based on such kind
of data, as well as the conceptual foundations of this area.
The topics of interest include (but are not limited to):
��� Semi-supervised learning
��� Weak label learning
��� Active learning
��� Partial label learning
��� Multi-label learning
��� Transfer learning
��� Few-shot learning
��� Zero-shot learning
��� Contrastive learning
Dates
Paper submission: January 14, 2022
Notification of Acceptance: March 1, 2022
Conference: July 11-15, 2022
Organizers
Any questions or remarks can be addressed to: