Prof. Jerry Chun-Wei Lin
IET Fellow, IEEE Senior Member
Western Norway University of Applied Sciences
Jerry Chun-Wei Lin is currently working as the full Professor at the Department of Computer Science, Electrical Engineering and Mathematical Sciences, Western Norway University of Applied Sciences, Bergen, Norway. He has published 500+ research papers in refereed journals with more than 80 IEEE/ACM journals. and international conferences. His research interests include data mining and analytics, soft computing, deep learning/machine learning, optimization, IoT applications, and privacy-preserving and security technologies.
Speech Title: Pattern-Driven Knowledge Discovery: Utility-Oriented Concepts
Abstract: As a large amount of data is collected daily from individuals, businesses, and other organizations or applications, various algorithms have been developed to identify interesting and useful patterns in data that meet a set of requirements specified by a user. The main purpose of data analysis and data mining is to find new, potentially useful patterns that can be used in real-world applications. For example, analyzing customer transactions in a retail store can reveal interesting patterns about customer buying behavior that can then be used for decision making. In recent years, the demand for utility-oriented pattern mining and analytics has increased because it can discover more useful and interesting information than basic binary-based pattern mining approaches, which has been used in many domains and applications, e.g., cross-marketing, e-commerce, finance, medical and biomedical applications. In this talk, I will first highlight the benefits by using the utility-oriented pattern mining and analytics compared to the past studies (e.g., association rule/frequent itemset mining). I will then provide a general overview of the state of the art in utility-oriented pattern mining and analytic techniques according to three main categories (i.e., data level, constraint level, and application level). Several techniques and modeling on different aspects (levels) of utility-oriented pattern mining will be presented and reviewed.
Prof. Yanan Sun
College of Computer Science, Sichuan University
Reasearch Area: Neural network, evolutionary computation, neural architecture search
Yanan Sun is currently a professor at the Department of Artificial Intelligence, College of Computer Science, Sichuan University, China. He obtained his Ph.D. degree from Sichuan University in 2017 and was a Postdoc Research Fellow of Victoria University of Wellington, New Zealand from 2017 to 2019. His research interests mainly include evolutionary computation, neural networks, and their applications in neural architecture search.
He has published ~50 peer-reviewed papers in top-tier conferences and journals, and most are published in IEEE TEVC, IEEE TCYB, IEEE TNNLS, NeurIPS, and ICCV. Among the publications, four have been both ranked as ESI TOP 1% Highly Cited Paper and ESI TOP 0.1% Hot Paper, and three have been selected as Research Frontier papers from IEEE CIS Newsletter. Dr. Sun has made contributions to the research field of neural architecture search. The indicator “GPU Day” measuring the algorithm complexity of neural architecture search algorithm was firstly proposed by Dr. Sun. The term “performance predictor” which is a new research direction to accelerate neural architecture search was also firstly proposed by Dr. Sun. In addition, Dr. Sun has also led the construction of the BenchENAS platform that provides neural architecture search as a benchmarking platform. Dr. Sun was ranked as World’s Top 2% Scientists in 2021 released by Sandford University and Elsevier.
Speech Title: Evolutionary Neural Architecture Search: Past and Future
Abstract：Deep Neural Networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process, and also not easy to realize due to the rare expertise in practice. Neural Architecture Search (NAS) is a type of technology that can design architectures automatically. Among different methods to realize NAS, Evolutionary Computation (EC) methods have recently gained much attention and success. In this talk, we will briefly summarize the EC-based NAS algorithms over 200 papers of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles as well as justifications on the design. In addition, current challenges and issues of EC-based NAS are also discussed to identify future research in this emerging field.
Prof. Jiawen Kang
School of Automation, Guangdong University of Technology
Reasearch Area: Blockchain, Artificial Intelligence, Internet of Things, Metaverse
Jiawen Kang is a Full Professor at Guangdong University of Technology. He was a postdoc at Nanyang Technological University, Singapore from 2018 to 2021. His research interests mainly focus on blockchain, metaverse, edge intelligence, security and privacy protection, etc. He has published around 100 research papers in leading journals and flagship conferences including 10 ESI highly cited papers and 3 ESI hot papers. He is the co-inventor of 15 granted patents and has won IEEE VTS Best Paper Award, IEEE Communications Society CSIM Technical Committee Best Journal Paper Award, IEEE Best Land Transportation Paper Award, IEEE HITC Award for Excellence in Hyper-Intelligence Systems (Early Career Researcher award), and 10 best paper awards of international conferences (e.g., WCNC 2020) as well. He is listed in the World’s Top 2% Scientists identified by Stanford University. He is now serving as the editor or guest editor for many leading journals including IEEE JSAC, TNSE, ISJ, and has also severed as the Co-chair of ICC Workshop, WCNC Workshop, ICDCS Workshop, Globcom 2021 Workshop, and HPCC Workshop, etc. He is a vice-chair of IEEE Technical Committee on Cognitive Networks Special Interest Group on "Wireless Blockchain Networks
Speech Title: Blockchain-based Federated Learning for Industrial Metaverses
Abstract：The emerging industrial metaverses realize the mapping and expanding operations of physical industry into virtual space for significantly upgrading intelligent manufacturing. The industrial metaverses obtain data from various production and operation lines by Industrial Internet of Things (IIoT), and thus conduct effective data analysis and decision-making, thereby enhancing the production efficiency of the physical space, reducing operating costs, and maximizing commercial value. However, there still exist bottlenecks when integrating metaverses into IIoT, such as the privacy leakage of sensitive data with commercial secrets, IIoT sensing data freshness, and incentives for sharing these data. In this talk, we introduce a user-defined privacy-preserving framework to improve privacy protection of industrial metaverse. A cross-chain empowered federated learning framework is further utilized to perform decentralized, secure, and privacy-preserving data training. Moreover, we introduce the age of information as the data freshness metric and thus design an age-based contract model to motivate data sensing among IIoT nodes.
Prof. Yang Yue
IEEE Senior Member
School of Information and Communications Engineering，Xi'an Jiaotong University
Reasearch Area: optical communications, optical perception, optical chip
Yang Yue is a Professor with the School of Information and Communications Engineering, Xi'an Jiaotong University, China. Dr. Yue’s current research interest is intelligent photonics, including optical communications, optical perception, and optical chip.
He has published over 200 peer-reviewed journal papers (including Science) and conference proceedings with >10,000 citations, five edited books, two book chapters, >50 issued or pending patents, >200 invited presentations (including 2 tutorial, >40 plenary and >50 keynote talks). Dr. Yue is a Senior Member of IEEE, Optica and SPIE. He is an Associate Editor for IEEE Access and Frontiers in Physics, Editor Board Member for four other scientific journals, Guest Editor for >10 journal special issues. He also served as Chair or Committee Member for >100 international conferences, Reviewer for >60 prestigious journals.
Title: Pre-calibration method for timing skew and power imbalance of coherent optical transmitter
Abstract: Power imbalance and timing skew among channels of coherent optical transmitter limits the transmission performance, especially for the latest 400-Gb/s or upcoming 1-Tb/s applications, which utilizes advanced modulation format and high baud rate. In this talk, we will introduce the experimental investigation results on the impact of IQ and XY power imbalances on various QAM formats and baud rates. Then, a convenient pre-calibration method based on optical interference will be discussed to detect and compensate both the timing skew and power imbalance.
Prof. Jinming Wen
Jinan University, China
Reasearch Area: lattice reduction and sparse recovery
Jinming Wen received the bachelor’s degree in information and computing science from the Jilin Institute of Chemical Technology, Jilin, China, in 2008, the M.Sc. degree in pure mathematics from Mathematics Institute, Jilin University, Jilin, China, in 2010, and the Ph.D degree in applied mathematics from McGill University, Montreal, QC, Canada, in 2015. He is currently a Professor with the College of Information Science and Technology and the College of Cyber Security, Jinan University, Guangzhou, China. He was a Postdoctoral Research Fellow with the Laboratoire LIP from March 2015 to August 2016, University of Alberta, Edmonton, AB, Canada, from September 2016 to August 2017, and University of Toronto, Toronto, ON, Canada, from September 2017 to August 2018. Since September 2018, he has been a Full Professor with Jinan University, Guangzhou, China. He has authored or coauthored more than 50 papers in top journals, including the Applied and Computational Harmonic Analysis, IEEE Transactions on Information Theory, IEEE Transactions on Signal Processing, and IEEE Transactions on Wireless Communications, and conferences.
Speech Title：Binary Sparse Signal Recovery with Binary Matching Pursuit
In numerous applications from communications and signal processing, we often need to acquire a $K$-sparse binary signal from sparse noisy linear measurements.In this talk, we first develop an algorithm called Binary Matching Pursuit (BMP) to recover the $K$-sparse binary signal. According to whether the residual vector is explicitly formed or not at each iteration, we develop two implementations of BMP which are respectively called explicit BMP and implicit BMP. We then analyze their complexities and show that, compared to the Batch-OMP, which is the fastest implementation of OMP, the improvements of the explicit and implicit BMP}algorithms are respectively $n/(2K)$ and $K$ times when some quantities are pre-computed. Finally, we provide sharp sufficient conditions of stable recovery of the support of the sparse signal using mutual coherence and restricted isometry property of the sensing matrix.