Impact Score 4.79
Graph features have the power to model and capture relationships between different data elements, probing a better investigation of complex data structure. Different from traditional hand-crafted features and deep features, graph features can be assigned to nodes to store node-specific information and/or edges where edge-specific attributes quantifying the relationship between two nodes are presented. Moreover, in real-world applications, the graph features are endowed with a dynamic nature. Furthermore, n this big data era, real-world graphs are usually large-scaled. However, it is well-known that the quadratic time complexity for graph construction might hinder graph learning for large-scale datasets. Hence, dynamic and large-scale graph learning require the development of more advanced techniques that overcome the limitations of existing machine learning and deep learning frameworks.
This special issue focuses on promoting the development of novel graph learning theory and techniques, specific platforms, and advanced methods to address the aforementioned challenges for graph learning on big data. To do this, this special issue will collect both surveys and research papers including but is not limited to:
The submissions of this special issue should follow the “Prior Publication Policy”. Specifically, the submissions should be original research papers that have not been previously published. However, the submissions can also be the extension version of conference papers published in English. Moreover, the journal version should have at least 30% difference from the conference version as well as should cite the conference version. In general, the submission cannot be an identical or nearly identical manuscript posted on a publically accessible archiving site (e.g., arXiv.org, etc.).
Authors should prepare their manuscript according to the “the Guide for Authors” available from the online submission page of Information Processing & Management .
Dr. Xiaofeng Zhu
Dr. Zhu is currently an associate professor at Massey University, New Zealand. His research interests include large scale image/video retrieval, feature selection, sparse learning, and medical image analysis. Dr. Zhu has published about 150 international research papers and were the recipients of ESI highly cited researcher 2019 and 2020. He is serving as an associate editor or editorial board member of three international journals, such as Neurocomputing, Journal of Ambient Intelligence and Humanized Computing, and International Journal of Data Mining and Bioinformatics, the managing guest editor of more than 10 international journals, such as Neurocomputing, World Wide Web Journal, Multimedia Systems Journal, Multimedia Tools and Applications, and Pattern Recognition Letters. Dr. Zhu was also the publicity co-chair of ACM MM 2021, the publication chair of the 9th International Frontiers of Algorithm Workshop (FAW2015) and the PC co-chair of the international conferences such as ICBK 2017 workshop DPD, the 18th International Conference on Electronic Business, and APWeb-WAIM 2019 Workshop.
Dr Islem Rekik
Dr Rekik is an Assistant Professor and the Director of the Brain And SIgnal Research and Analysis (BASIRA) laboratory (http://basira-lab.com/), at Istanbul Technical University. She completed her PhD at the University of Edinburgh in 2014, UK, and enjoyed two years of post-doctoral fellowship at IDEA lab, University of North Carolina from 2014-16. She has been an honorary researcher at the School of Science and Engineering at the University of Dundee since 2018. In 2019, she was awarded the 3-year prestigious TUBITAK 2232 for Outstanding Experienced Researchers fellowship and in 2020 she became a Marie Skłodowska-Curie Fellow under the European Horizons 2020 program. In 2019, she was elected as the president of the Women in MICCAI (WiM) president. She served as a program committee member of leading international medical image analysis conferences and workshops including MICCAI, IPMI and area chair of MICCAI 2019-2020 and the international conference on Medical Imaging with Deep Learning (MIDL) 2019, London, UK. She co-organized Predictive Intelligence in MEdicine (PRIME) in conjunction with MICCAI 2018-2020 along with other workshops (CNI, ShapeMI). She is the author of more than a hundred peer reviewed scientific papers. She is author of more than 7 awarded papers including 6 at MICCAI and 1 at ATSIP. Her research work aims to design a predictive intelligence for improving healthcare and wellbeing as well as decoding the human brain.
Dr. Kim received her B.S., M.S. and Ph.D. degrees in Computer Science Engineering from Ewha Womans University, Seoul, Korea. Before she joined the Department of Computer Science at University of North Carolina at Greensboro in 2018 as an assistant professor, she was a postdoctoral researcher and research associate in Biomedical Research Imaging Center (BRIC) and Department of Radiology, University of North Carolina at Chapel Hill since 2009. She was also a visiting researcher in University of Pennsylvania, Fraunhofer-IGD (Germany) and University of Hamburg-Eppendorf (Germany). Dr. Kim’s research interests are mainly in developing cutting-edge image analysis methods for the interdisciplinary field between computer science and biomedicine. Imaging data has become the most powerful tool in biomedicine due to the advancement of high-resolution imaging technology and the increasing variety of imaging modalities. She aims to apply state-of-the-art computer science technologies, for example, machine/deep learning, pattern recognition, computer vision, visualization, and graph theory, to various clinical and preclinical research imaging data to study biomedical fundamentals from computer scientists’ view. Such techniques can be adapted to healthcare practices and biomedical research for automated image reading/quantification, computer-assisted diagnosis at an earlier time as well as predictive modeling for clinical outcome. Dr. Kim’s research has been supported by Google Education and the Ministry of Science and Technology of Korea. She has been serving as the editorial board member of KSII Transactions on Internet and Information Systems and the guest editor of Neurocomputing, The Computer Journal, and Neural Computing and Applications. She has been serving as the program committee member for conferences in the fields of medical image analysis, multimedia and machine learning. She has also been serving as a review for top-tier journals and international conferences, for example, Medical Image Computing and Computer Assisted Intervention (MICCAI), IEEE Transactions on Medical Imaging IEEE Transactions on Image Processing, IEEE Transactions on Biomedical Engineering, Medical Image Analysis, Pattern Recognition, Artificial Intelligence in Medicine, Magnetic Resonance in Medicine, etc.