[DBWorld] Call for Paper: Special Issue on Multi-view Learning

Call for Papers: Special Issue on Multi-view Learning

Background

With advances in information acquisition technologies, multi-view data are increasing dramatically in a variety of forms, such as text and sound, text and images, text in different languages, etc. The different views contain complementary and consensus information. To make full use of this information, many multi-view learning paradigms have appeared, such as multi-view classification, multi-view semi-supervised learning, multi-view clustering, multi-view representation learning, and a variety of deep learning techniques.

Although multi-view learning has gained great success in the past two decades, there are still many open problems that require further investigation. For example, most existing multi-view learning methods cannot deal with missing values directly. Multi-view clustering lacks stability due to initialization. The big data era calls for more scalable and efficient multi-view approaches. Deep learning technology may bring some new strategies to integrate multiple views. All these call for novel multi-view learning theory and algorithms.

Multi-view learning has been successfully applied to subfields in many applications like computer vision, natural language processing, social network, health, biology, economics, marketing, finance. Extending its application to more subfields needs more novel advanced multi-view learning theory and algorithms, especially deep ones.  

Scope and Topics of Interest

We welcome novel, innovative, state-of-the-art, original, creative, applicable, and cutting-edge contributions on the following topics, but not limited to:

Multi-view feature representation learning
Large scale multi-view learning algorithm design
Multi-view learning approaches to deal with missing values and noisy samples
Novel theory for multi-view learning
Multi-view learning for graphs and relational data 
New strategies to integrate multiple views
Views weighting or views selection
Visualization of multi-view data
Multi-view learning and its application in medical informatics, computer vision, natural language processing, etc. 
Relationship to transfer learning, multi-task learning, ensemble learning
New High quality multi-view data sets
Multi-view learning for pandemic and covid-19 data modeling
All accepted manuscripts are expected to solve or partially solve one of the open problems in multi-view learning or inspire new ideas to help advance multi-view learning further. Each of the submitted papers will be reassigned at least three reviewers nominated by the committee of the proposed editors of this special issue.

Important Dates

Submission deadline: July 10, 2021

First notification: August 30, 2021

Second notification: October 30, 2021

Final decision: November 30, 2021

Additional Details:
https://www.springer.com/journal/10489/updates/18881306
_______________________________________________
Please do not post msgs that are not relevant to the database community at large.  Go to www.cs.wisc.edu/dbworld for guidelines and posting forms.
To unsubscribe, go to https://lists.cs.wisc.edu/mailman/listinfo/dbworld