Guest Editorial: Special issue on machine learning and deep learning algorithms for complex networks

In the latest years, researchers from the industry and academia extensively applied machine learning algorithms in a broad range of domains. The goal of this special issue is to illustrate the most recent applications of deep learning methods in a range of real-life domains and to show the practical utility of these techniques. A particular attention goes towards methods to process network data that is capable of modelling complex artificial and natural systems as the interactions of a multitude of simpler entities. The first paper of this special issue is by Du et al., which deals with an intriguing (and quite unexplored research question): can we use deep neural networks to make time series prediction? The authors combine a well-known statistical model called State Space Model (SSM) with deep neural networks to obtain a time series forecasting model called Deep Nonlinear State Space Model (DNLSSM). Their experimental results show the superiority of DNLSSM against a broad range of competitors on both real and synthetic datasets. The second paper by Maurya et al. introduces a significant advancement in the feature aggregation step performed in Graph Neural Networks (GNNs). It is well known, in fact, that GNNs can generate rich node representations by aggregating the feature of a node with the features of its neighbours and features of ‘distant’ nodes might be poorly correlated with the feature of the node we wish to represent. As such, the indiscriminate aggregation of features favours the propagation of noise, and ultimately, it degrades the performance of a GNN. The authors introduce a new architecture (called Dual-Net GNN), which selectively combines node features at different hops. The experiment results indicate that such a technique outperforms the state-of-the-art baselines over many real-world datasets. The third paper by Yan et al. introduces a new low-carbon economic dispatching model. The proposed model takes into account the impact of carbon emissions and is able to model randomness of wind power generation. The authors apply the ant-lion optimization algorithm based on the Levy flight mechanism and golden sine to find the optimal configuration. The obtained algorithm quickly converges and is robust, thus proving to be applicable in real-life scenarios. The fourth paper, by Mahmood et al., aims at investigating the role of complex q-rung orthopair normal fuzzy (CQRONF) information in supply chain management. The authors propose a multi-attribute decision-making tool for finding a beneficial sustainable supplier to handle complex dilemmas and they illustrate the effectiveness of the proposed approach through a comparative analysis. The fifth paper is by Li et al., which applies deep reinforcement learning to realize autonomous manoeuvre decision-making of UAV in one-to-one air combat. The authors start from the popular non-deterministic Soft-Actor-Critic (SAC) algorithm to train an intelligent combat UAV with cognitive capabilities that can perceive and recognise a battlefield. Their experimental results demonstrate that the proposed method increases the generalisation ability of the environment and helps realize migration training. The last paper of this collection is by Mukherjee et al., which describes two approaches to predicting stock market indices as well as stock prices. The first approach exploits a deep-forward Neural Network. It achieves a good prediction accuracy, but it also needs a large amount of training data and computational resources. The second approach applies a Convolution Neural Network model and it significantly reduces the demand of computational resources as well as training data while achieving a good accuracy. These selected papers cover interesting topics and present some of the key directions in this important area of research and development. We hope that the set of selected papers provides the community with a better understanding of the current directions and areas to focus in future. We thank all the authors for considering this special section as an outlet to publish their research results and would like to thank the referees who provided very useful and thoughtful feedback to the authors. We also express our gratitude to the IET staff members for their kind support, advice, and encouragement throughout the preparation of this special issue. The data that support the findings of this study are available on request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions. Pasquale De Meo is an associate professor of computer science with the Department of Computer Science, University of Messina, Italy. His main research interests include social networks, recommender systems, and user profiling. His PhD thesis was selected as the Best Italian PhD thesis in artificial intelligence by the AI*IA (Italian Association for Artificial Intelligence). He has been the Marie Curie fellow at Vrije Universiteit Amsterdam. He serves as an associate editor for the IEEE Transactions on Cybernetics. More information about his research can be found at http://dblp.uni-trier.de/pers/hd/m/Meo:Pasquale_De. Qun Jin received the B.S. degree in control engineering from Zhejiang University, China, in 1982, and received the Ph.D. degree in electrical engineering and computer science from Nihon University, Japan, in 1992. He is currently a Professor in the Department of Human Informatics and Cognitive Sciences, Faculty of Human Sciences, Waseda University, Japan. He has been extensively engaged in research works in the fields of computer science, information systems, and human informatics, with a focus on understanding and supporting humans through technologies. His recent research interests cover big data, artificial intelligence, machine learning, blockchain, cyber security, digital twin, metaverse, behavior and cognitive informatics, and computing for human well-being. He is a foreign fellow of the Engineering Academy of Japan (EAJ). Michael Sheng is a full Professor and Head of Department of Computing at Macquarie University, Sydney, Australia. His research interests include service oriented computing, distributed computing, Internet computing, machine learning, and Internet of Things. Michael holds a PhD degree in computer science from the University of New South Wales (UNSW) and did his post-doc as a research scientist at CSIRO ICT Centre. Prof Michael Sheng is the recipient of the AMiner Most Influential Scholar Award on IoT (2019), ARC Future Fellowship (2014), Chris Wallace Award for Outstanding Research Contribution (2012), and Microsoft Fellowship (2003). He is the Vice Chair of the Executive Committee of the IEEE Technical Community on Services Computing (IEEE TCSVC). Jianguo Yao obtained his Ph.D degree at Northwestern Polytechnical University in 2010, and was a joint-education Ph.D student at McGill University from 2007 to 2008. He was also a joint Postdoctoral Fellow at Ecole Polyechnique de Montreal and McGill University from 2011 to 2012. In 2011, he worked briefly as an intern researcher at Bombardier Inc. in Canada. In 2015, he worked as a visiting professor at Technische Universität München in Germany. He received the prestigious Alexander von Humboldt Fellowship and PBEEE/Quebec Merit Scholarship for Foreign Students from Quebec Fund for Research on Nature and Technology (FQRNT). Dr. Yao is an Associate Dean of School of Software, and a full Professor at the Shanghai Jiao Tong University (SJTU), Shanghai, China, and he directs the Automatic Computing Group at SJTU. His research interests are distributed systems, virtualization in clouds and industrial big data. He has published more than 50 research papers in major peer-reviewed International journals and top-conference proceedings, including Proceedings of the IEEE, ACM/IEEE Transactions (TPDS, TDSC, TSC, TII, TIE, TSG, TACO, TECS, TSN), RTSS, VLDB, ATC, KDD, INFOCOM, ICDCS, HPDC etc. He is very active with the Cloud and Data communities. He has participated in various conferences, and served as Publicity Co-Chairs in the conferences including Middleware 2016, ICAC 2016, and TPC members in the conferences including: DAC 2021‘2022, INFOCOM 2014’2015’2016’2017, ICDCS 2015’2017-2019, Middleware 2017, ACM e-Energy 2017, SIES 2013, RTCSA 2012’2013 and ICPADS 2012 etc. He is a Senior Member of IEEE.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.