Aims and Scope:
Graph provides a natural way to represent and model the structure or connection properties of data across any scientific and industrial field, such as social networks, economic networks, information networks, biomedical knowledge graphs, and internet graphs. Given the widespread prevalence of graphs, graph representation learning plays an important role in machine learning, with applications in clustering, recognition, information retrieval, recommendation, knowledge discovery, and others. Learning graph-structured representations on large-scale multimedia data have been intensively exploited and attracted broad interests due to its fundamental advantages in supporting transferability, interpretability, causality, and inductive/transductive exploration.
Recent years have witnessed a surge in research on graph representation learning under the umbrella terms of manifold learning (such as graph-based dimensionality reduction) and deep learning (such as graph convolutional neural networks). The general idea behind these approaches is to learn representations that encode structural information onto a low-dimensional embedding space, which can reflect the geometric relationships of the original graph. However, the current researches are still far from satisfactory in flexible modeling of graphs on big data, scalable learning with very large graphs, and efficient optimization on big graphs. As such, many new applications and algorithms on graphs are emerging to cater for the needs of processing and understanding large-scale multimedia data.
This suggests that this topic has reached critical mass and requires a focused special session to identify influential areas of interest, and discuss how we can design new and better benchmarks, establish advanced theoretical foundations, discuss empirical discoveries and foster collaboration. The objective of the special issue is thus to provide an opportunity for researchers and engineers from both academia and industry to publish their latest and original results on graph representation learning models, algorithms and applications for large-scale multimedia analytics.
Topics of Interests:
The list of possible topics includes, but not limited to:
Deep learning methods on graphs/manifolds for multimedia analysis
Efficient graph-based clustering/ranking/retrieval/classification on multimedia data
Graph generative networks for multimedia analysis
Graph convolution networks for multimedia analysis
Graph attention networks for multimedia analysis
Graph autoencoders for multimedia analysis
Unsupervised/semi-supervised graph/manifold learning on multimedia data
Factorization methods for graph embedding techniques on multimedia data
Optimization methods for graphs/manifolds for multimedia analysis
Theoretical analysis of deep learning models for graphs/manifolds
Benchmark multimedia datasets and evaluation metrics
Papers should be submitted electronically using the Elsevier submission system to Information Processing & Management (https://www.evise.com/profile/#/IPM/login) and following the Journal submission guidelines. When submitting the manuscript please select the article type “VSI: GRL4LMA” as the Article Type to ensure your manuscript be correctly assigned. Please submit your manuscript before the submission deadline.
The proposed schedule is given below:
Paper submission deadline: June 31, 2020
First review notification: August 31, 2020
Revision submission: October 15, 2020
Second review notification: November 30, 2020
Acceptance notification: December 31, 2020
Dr. Zheng Zhang, Harbin Institute of Technology, Shenzhen, China (email@example.com)
Dr. Xiaofeng Zhu, Massey University, New Zealand (firstname.lastname@example.org)
Dr. Jingkuan Song, University of Electronic Science and Technology of China, China (email@example.com)
Dr. Ehsan Adeli, Stanford University, USA (firstname.lastname@example.org)
Brief CV of Guest Editors
Zheng Zhang is currently an Assistant Professor at the School of Computer Science & Technology, Harbin Institute of Technology, Shenzhen, China. Prior to this, he received his M.S. degree in Computer Science (2014) and Ph.D. degree in Computer Applied Technology (2018) from the Harbin Institute of Technology. His Ph.D. thesis was awarded the Distinguished Ph.D. Dissertation of The Chinese Institute of Electronics (CIE) and also received the Distinguished Doctor Degree Thesis Award of Harbin Institute of Technology. He visited the National Laboratory of Pattern Recognition (NLPR) at Chinese Academy of Sciences (CAS), Beijing, working with Prof. Cheng-Lin Liu (Director of the Laboratory, IEEE Fellow and IAPR Fellow), from Jun. 2015 to Jun. 2016. Dr. Zhang was a Research Associate at The Hong Kong Polytechnic University from Apr. 2018 to Oct. 2018, and then joined in School of Information Technology and Electrical Engineering, The University of Queensland, Australia, as a Postdoctoral Research Fellow from Oct. 2018 to Sep. 2019. He has published over 50 technical papers at prestigious international journals and conferences, including the IEEE TPAMI, IEEE TNNLS, IEEE TIP, IEEE TCSVT, Neural Networks, Pattern Recognition, IEEE CVPR, ECCV, AAAI, IJCAI, SIGIR, ACMM, ICDM, etc. He serves as a Guest Editor of Neurocomputing, a Publication Chair of the 16th International Conference on Advanced Data Mining and Applications (ADMA 2020), and an SPC/PC member of several top conferences. He works were recognized as the Young Outstanding Research Achievement Award of Chinese Association for Artificial Intelligence (CAAI) and the Best Paper Award from the 2014 International Conference on Smart Computing (SMARTCOMP). His current research interests include machine learning, computer vision, and multimedia analytics. He is a member of IEEE, ACM, and AAAI.
Xiaofeng Zhu is currently an Associate Professor of Big data/computer science at the Institute of Natural and Mathematical Sciences, Massey University Albany Campus, New Zealand. Before joining Massey University, I worked at the University of Pennsylvania and University of North Carolina at Chapel Hill, and received my Ph.D. degree in computer science from The University of Queensland, Australia. My research interests include machine learning and image analysis. Specifically, I am focusing on mining useful knowledge or information from big multimedia data and medical imaging data.
Jingkuan Song is a full professor with the University of Electronic Science and Technology of China (UESTC). He joined Columbia University as a Postdoc Research Scientist (2016-2017), and the University of Trento as a Research Fellow (2014-2016). He obtained his Ph.D. degree in 2014 from The University of Queensland (UQ), Australia (advised by Prof. Heng Tao Shen). His research interest includes large-scale multimedia retrieval, image/video segmentation and image/video understanding using hashing, graph learning, and deep learning techniques. He was the winner of the Best Paper Award in ICPR (2016, Mexico), Best Student Paper Award in the Australian Database Conference (2017, Australia), and Best Paper Honorable Mention Award (2017, Japan). He is the Guest Editor of TMM, WWWJ and he is PC member of CVPR’18, MM’18, IJCAI’18, etc. Ehsan Adeli is currently a researcher and NIH Fellow at Stanford University, working at the intersection of Machine Learning, Computer Vision, Computational Neuroscience, and Medical Image Analysis in the School of Medicine and the Stanford AI Lab (SAIL). Previously, he was a postdoctoral research associate at the University of North Carolina. During his Ph.D. studies, he was also a research scholar at the Robotics Institute, Carnegie Mellon University, Pittsburgh, PA. Dr. Adeli’s research interests include machine learning, computer vision, medical image analysis and computational neuroscience.