Top Research Papers on Networking

Current GNN-based methods are reviewed, highlighting the ways that they have been used in several applications related to brain graphs such as missing brain graph synthesis and disease classification, and charting a path toward a better application of GNN models in network neuroscience field for neurological disorder diagnosis and population graph integration.

This work discusses briefly the types of molecular data that are used in molecular network analyses, survey the analytical methods for inferring molecular networks, and review efforts to validate and visualize molecular networks.

The SDN is reviewed; it introduces SDN, explaining its core concepts, how it varies from traditional networking, and its architecture principles, and the crucial advantages and challenges of SDN are presented, focusing on scalability, security, flexibility, and performance.

An artificial intelligence (AI)-native network slicing architecture for 6G networks is presented to enable the synergy of AI and network slicing, thereby facilitating intelligent network management and supporting emerging AI services.

An algorithm named Network Embedding for node Clustering (NEC) to learn network embedding for node clustering in attributed graphs and introduces soft modularity, which can be easily optimized using gradient descent algorithms, to exploit the community structure of networks.

This minireview provides an overview of the recent developments of bioinspired DN hydrogels defined as DN hydhydrogels that mimic the properties and/or structure of natural tissue, ranging from, e.g., anisotropically structured DNHydrogels, via ultratough energy dissipating DN Hydrogels to dynamic, reshapable DN hyd rogels.

This tutorial paper looks into the evolution and prospect of network architecture and proposes a novel conceptual architecture for the 6th generation (6G) networks, which can facilitate three types of interplay, i.e., the interplay between digital twin and network slicing paradigms, between model-driven and data-driven methods for network management, and between virtualization and AI.

An overview of the construction method of wireless communication graph for various wireless networks and the progress of several classical paradigms of graph neural networks are introduced, as well as several applications of GNNs in wireless networks such as resource allocation and several emerging fields.

This paper makes the first attempt to study network schema preserving HIN embedding, and proposes a novel model named NSHE, which significantly outperforms the state-of-the-art methods.

The Network Society is now more than ever the essential guide to the past, consequences and future of digital communication. Fully revised, this Third Edition covers crucial new issues and updates. This book remains an accessible, comprehensive, must-read introduction to how new media function in contemporary society.

The question of agency has been neglected in social network research, in part because the structural approach to social relations removes consideration of individual volition and action. However, recent emphasis on purposive individuals has reignited interest in agency across a range of social network research topics. Our paper provides a brief history of social network agency and an emergent framework based on a thorough review of research published since 2004. This organizing framework distinguishes between an ontology of dualism (actors and social relations as separate domains) and an ontol...

This paper presents the Discrete Case: Multinomial Bayesian Networks and the Continuous Case: Gaussian Bayesian networks, both of which areagnostic of the discrete and continuous cases.

This report is devoted to a comprehensive review of resilience function and regime shift of complex systems in different domains, such as ecology, biology, social systems and infrastructure, and discusses some ambiguous definitions, including robustness, resilience, and stability.

This Review Article summarizes progress in network geometry, its theory, and applications to biological, sociotechnical and other real-world networks and offers perspectives on future research directions and challenges in this frontier in the study of complexity.

The fitness landscape analysis verifies that the transformed community detection problems have smoother landscapes than those of the original problems, which justifies the effectiveness of the proposed graph neural network encoding method.

This survey presents a comprehensive analysis of the exploitation of network slicing in IoT realisation and discusses the role of other emerging technologies and concepts, such as blockchain and Artificial Intelligence/Machine Learning (AI/ML) in network slicing and IoT integration.

This work presents BrainGB, a benchmark for brain network analysis with GNNs, a standardizes the process by summarizing brain network construction pipelines for both functional and structural neuroimaging modalities and modularizing the implementation of GNN designs.

Thermal district networks are effective solutions to substitute fossil fuels with renewable energy sources for heating and cooling. Moreover, thermal networking of buildings allows energy efficiency to be further increased. The waste heat from cooling can be reused for heating in thermal district systems. Because of bidirectional energy flows between prosumers, thermal networks require new hydraulic concepts. In this work, we present a novel network topology for simultaneous heating and cooling: the reservoir network. The reservoir network is robust in operation due to hydraulic decoupling of ...

The proposed NFN＋ model, to the best knowledge, achieved the state-of-the-art retinal vessel segmentation accuracy on color fundus images (AUC: 98.30%, 98.75% and 98.94%, respectively).

Gene regulatory networks (GRNs) encode the complex molecular interactions that govern cell identity. Here we propose DeepSEM, a deep generative model that can jointly infer GRNs and biologically meaningful representation of single-cell RNA sequencing (scRNA-seq) data. In particular, we developed a neural network version of the structural equation model (SEM) to explicitly model the regulatory relationships among genes. Benchmark results show that DeepSEM achieves comparable or better performance on a variety of single-cell computational tasks, such as GRN inference, scRNA-seq data visualizatio...

It has been proposed to move from hypotheses supporting an overall hemispheric specialization for emotion processing toward dynamic models incorporating multiple interrelated networks which do not necessarily share the same lateralization patterns.

Simulation results for energy-efficient networking show that better gains in network energy efficiency can be achieved by the joint optimization between industrial data centers and industrial cloud networks.

With the widespread popularization of social network platforms, user-generated content and other social network data are growing rapidly. It is difficult for social users to select interested contents from the numerous social data. To alleviate information overload problem and enhance overall user experience of social networks, recommendation systems relying on historical behavioural data and social friendship relations of users, are widely used in social networks. Although researches on social recommendations have been conducted in recent years, recommendation systems of social networks still...

This paper proposes RouteNet, a novel network model based on Graph Neural Network that is able to understand the complex relationship between topology, routing, and input traffic to produce accurate estimates of the per-source/destination per-packet delay distribution and loss.

One-class graph neural network (OCGNN), a one-class classification framework for graph anomaly detection, which is designed to combine the powerful representation ability of graph neural networks along with the classical one- class objective.

It is demonstrated how this branch of machine learning can benefit multiple aspects of computer and communication networks, including mobile networks, network analysis, internet of things, physical layer, and cybersecurity.

This paper proposes a novel Hierarchical Road Network Representation model, named HRNR, by constructing a three-level neural architecture, corresponding to "functional zone", "structural regions" and "road segments", respectively, and designs aThree-level hierarchical update mechanism for learning the node embeddings through the entire network.

Inspired by the concept of graph convolutional networks, a simply yet effectively method named R C N N is presented to identify critical nodes with the best spreading ability and shows that under Susceptible–Infected–Recovered (SIR) model, this method outperforms the traditional benchmark methods.

A network-slicing based architecture is introduced and why and where artificial intelligence (AI) should be incorporated into this architecture and the benefits and potentials of AI-based approaches in the research of NGWNs are highlighted.

Academic networks have been found to play a significant role in career trajectory via employment opportunities, publishing openings, or being alerted to prospects not widely advertised. These results are reflective of Bourdieu's notion that social capital can see an individual's position within a field (in this article the field of academia) increase due to their network's aggregate resources, which can be leveraged and see them attain success they may not have been able to achieve without their network's capital and collective field position. This study surveyed more than 100 working academic...

The success of GNNs in extrapolating algorithmic tasks to new data relies on encoding task-specific non-linearities in the architecture or features, and a hypothesis is suggested for which theoretical and empirical evidence is provided.

A network intrusion detection algorithm combined hybrid sampling with deep hierarchical network is proposed, which uses convolution neural network to extract spatial features and Bi-directional long short-term memory to extract temporal features, which forms aDeep hierarchical network model.

More stringent thresholding resulted in more age-sensitive network measures in five of the six network weightings, except at the highest levels of sparsity, where crucial connections were then removed.

The results confirm that the model is very efficient in recognition of potential threats reaching above 99% of accuracy even in a case of reduced number of evaluated networking features.

This article proposes an efficient online service function chain deployment (OSFCD) algorithm that selects the path to deploy that is close to the SFC length and shows that the OSFCD algorithm optimizes multiple performance indicators of online SFC deployment.

This work identifies specific node definition and thresholding procedures that neuroscientists can follow in order to derive representative networks from their human neuroimaging data by minimizing an information-theoretic measure of divergence between network topologies, known as the portrait divergence.

A scalable DT of network slicing is developed, aiming to capture the intertwined relationships among slices and monitor the end-to-end (E2E) metrics of slices under diverse network environments, and exploits the novel graph neural network model that can learn insights directly from slicing-enabled networks represented by non-Euclidean graph structures.

AbstractIn this paper, we adopt a dynamic perspective on networks and creativity to propose that the oft-theorized creative benefits of open networks and heterogeneous content are less likely to be...

A deep learning model is proposed, named InfGCN, to identify the most influential nodes in a complex network based on Graph Convolutional Networks, which significantly outperforms traditional methods, and can accurately identify influential nodes.

Spiking neural networks (SNNs) are biology-inspired artificial neural networks (ANNs) that comprise of spiking neurons to process asynchronous discrete signals. While more efficient in power consumption and inference speed on the neuromorphic hardware, SNNs are usually difficult to train directly from scratch with spikes due to the discreteness. As an alternative, many efforts have been devoted to converting conventional ANNs into SNNs by copying the weights from ANNs and adjusting the spiking threshold potential of neurons in SNNs. Researchers have designed new SNN architectures and conversio...