The workshop on Learning from difficult data streams is organized under the framework of

The International Joint Conference on Neural Networks (IJCNN) IJCNN 2020 (as a part of WCCI 2020)

The workshop will be held in Glasgow, Scotland July19-24 2020.

Aim and Scope

Difficulties embedded within characteristics of real-life data pose various challenges to contemporary machine learning algorithms. This session will mainly focus on learning from data streams, with special focus paid to the accompanying data difficulties, such as presence of concept drift, lack of information about labels, imbalanced data distributions, insufficient numbers of learning instances, missing data etc., to enumerate only a few. The main aim of this section is to bring together researchers from basic computing disciplines (computer science and mathematics) and from various application areas who are pioneering data analysis methods in sciences, as well as in humanitarian fields, to discuss problems and solutions in the area of data difficulties, to identify new issues, and to shape future directions for research. The use of neural networks and deep learning due to their universality and online nature is a highly sought-after direction. Unfortunately, neural models have also their in-built limitations, associated with the stability and plasticity dilemma or catastrophic forgetting.

The list of possible topics includes, but is not limited to:

• machine learning models for data streams
• neural networks for streaming and evolving data
  • stability and plasticity dilemma
  • avoiding catastrophic forgetting phenomenon
  • online learning strategies
  • deep learning for streaming and drifting data
• learning in the presence of concept drift
• class imbalanced learning in data streams
• learning in the presence of emerging and disappearing classes
• ensemble learning for drifting data streams
• concept drift detection
• learning with limited ground truth access
• learning from high dimensional data streams
• learning on the basis of limited data sets, including one-shot learning
• instance and prototype selection under non-stationary conditions
• data imputation methods for evolving data
• case studies and real-world applications affected by data difficulties

Important Dates

• Paper Submission: January 15, 2020
• Notification of Acceptance: March 15, 2020
• Camera Ready Deadline: April 15, 2020
• Conference Dates: July 19-24, 2020

Submission Guidelines

This special session will be held in 2020 International Joint Conference on Neural Networks (IJCNN) (wcci2020.org/ijcnn-sessions/), part of 2020 IEEE World Congress on Computational Intelligence (https://wcci2020.org/ ) (Glasgow, Scotland, United Kingdom, July 19-24, 2020).

All papers should be prepared according to the IJCNN 2020 policy and should be submitted electronically using the conference website (https://wcci2020.org/submissions/) .

To submit your paper to this special session, you will use the IJCNN upload link and choose our special session "Learning from difficult data streams" in the research topic list.

All papers accepted and presented at IEEE IJCNN/WCCI 2020 will be included in the conference proceedings published by IEEE Explore, which are typically indexed by EI.

Session Chairs

• Bartosz Krawczyk (bkrawczyk@vcu.edu), Virginia Commonwealth University, USA
• Michal Wozniak (michal.wozniak@pwr.edu.pl), Wroclaw University of Science and Technology, Poland