Special Issue on Advanced Learning for Large-Scale Heterogeneous Computing
Aims and Scope: Coming with the era of big data, nowadays we have witnessed a drastic growth of heterogeneous data information involved in scalable computing and analysis. It has opened up a new gate and aroused new challenges in developing effective machine learning technologies to cater for such a heterogeneous computing requirement. Exemplar scenarios include, but not limited to, cross-modality visual search, machine translation, multi-modality medical imaging, and analyzing heterogeneous generic features. Under this circumstance, hybrid data comes from multiple sources, and is also typically hybrid in different feature channels. This requires a specific treatment covering different stages like data acquisition, storage, filtering, knowledge discovery, and classifier training. Among almost all stages above, principled machine learning techniques are indeed strongly expected for intelligent knowledge representations and smart decisions. To this end, advanced machine learning techniques have developed quickly in recent years. Several influential new methods were reported in established journals. For example, affinity propagation was published in Science for data clustering; extreme learning machine was published in Neurocomputing, quickly becoming the most cited and downloaded paper after its official publication. In the latest years, we have encountered the wave of a variety of machine learning algorithms and frameworks, ranging from deep learning to quantum learning machines. It therefore becomes vital to report the very recent progress in advanced machine learning methodologies and state-of-the-arts for handling large-scale heterogeneous data. We are targeting at inviting original research works in this field, covering new theories, new algorithms, new implementations, new benchmarks, and new industrial deployments concentrating on the topic, Large-Scale Heterogeneous Computing. More specifically, we are also targeting at inviting top-tier and established researchers to contribute one or more survey papers, as well as comprehensive discussions and outlooks on potential directions. This special issue will report the recent large-scale machine learning techniques and related applications. Papers from the following topics would be highly welcome, i.e., novel classification and clustering algorithms, such as strategies for dealing with large-scale hybrid and heterogeneous data, methods for large-scale imbalanced learning, methods for multiple view learning, methods for semi-supervised learning, methods for multiple kernel learning, etc. Large-scale applications in multimedia and biological hybrid data are especially encouraged. We also encourage authors to supply their codes and release their real-world datasets, which would impact on our issue more significantly. Please do not evaluate your algorithms only on UCI or small benchmark datasets. The editors look forward to collecting a set of recent advances in the related topics, to provide a platform for researchers to exchange their innovative ideas and real heterogeneous data. Submission Instruction: Authors should prepare their manuscript according to the Guide for Authors available from the online submission page of the Neurocomputing journal at http://www.journals.elsevier.com/neurocomputing/. Authors should choose “SI: ALLSHC” under Article Type. All the papers will be peer-reviewed following the Neurocomputing reviewing procedures. Topics of Interest: - Large-scale classification algorithms with applications
- Large-scale clustering algorithms with applications
- Deep learning methods for hybrid and heterogeneous data
- Imbalanced learning methods for bioinformatics data
- Multiple view leaning methods for image classification
- Semi-supervised learning methods for big hybrid data
- Ensemble learning methods for big hybrid data
- Parallel learning methods for ultra-large data
- Multiple kernel learning methods with applications
- Multiple label classification algorithms with applications
- Extreme learning methods and applications to big multimedia or biological data
Important Dates - Paper Submission: Nov. 1, 2015
- First Round Notification: Dec. 1, 2015
- Revision: Jan. 1, 2016
- Final Decision: Feb 1, 2016
- Publication Date: Apr. 1, 2016
Guest Editors Quan Zou
Professor
School of Computer Science and Technology
Tianjin University, Tianjin 300072, China
zouquan@nclab.net Wei Liu
Researcher
IBM T. J. Watson Research Center
Yorktown Heights, NY 10598, USA
weiliu@us.ibm.com Michele Merler
Researcher
IBM T.J. Watson Research Center
Yorktown Heights, NY 10598, USA
mimerler@us.ibm.com Rongrong Ji
Professor
School of Information Science and Engineering
Xiamen University, Xiamen 361005, China
rrji@xmu.edu.cn
|
发表于 2015-10-3 09:16:09