Top Research Papers on Networking

The results of applying the artificial neural networks methodology to acute nephritis diagnosis based upon selected symptoms show abilities of the network to learn the patterns corresponding to symptoms of the person.

Network Analysis is an introduction to both the why and how of Social Network Analysis, which presents a broad theoretical overview rooted in social scientific approaches and guides users in how network analysis can answer core theoretical questions.

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.

A reproducible GNN benchmarking framework is introduced, with the facility for researchers to add new models conveniently for arbitrary datasets, and a principled investigation into the recent Weisfeiler-Lehman GNNs (WL-GNNs) compared to message passing-based graph convolutional networks (GCNs).

KANs are promising alternatives for MLPs, opening opportunities for further improving today's deep learning models which rely heavily on MLPs.

The emergence of the Mobile Ad Hoc Networking (MANET) technology advocates self-organized wireless interconnection of communication devices that would either extend or operate in concert with the network.

A fast proof-of-concept that the 3-order B-splines used in Kolmogorov-Arnold Networks (KANs) can be well approximated by Gaussian radial basis functions leads to FastKAN, a much faster implementation of KAN which is also a radial basis function (RBF) network.

A comprehensive overview of cognitive communications in wireless sensor networks, this work lays the foundations for readers to participate in a new era of research in this emerging field.

The results illustrated the success of the developed model in identifying various fault conditions and system parameters on the Gwagwalada-Katampe 330kV transmission line, modelled using MATLAB Simulink.

This chapter examines how Blockchain can be used with cooperative networks and how it could fundamentally alter the way entities interact and communicate and demonstrates the real-world effects of Blockchain-enabled collaborative networks across various industries with a number of case studies.

,

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.

A new methodology to automatically define the allocation scheme and configuration of packet filters in the logical topology of a virtual network is proposed, based on solving a carefully designed partial weighted Maximum Satisfiability Modulo Theories problem by means of a state-of-the-art solver.

This examination underscores the potential of counterfeit insights models utilizing neural systems in diagnosing cases requiring gastric surgery.

This work proposes to represent neural networks as computational graphs of parameters, which allows them to harness powerful graph neural networks and transformers that preserve permutation symmetry, and enables a single model to encode neural computational graphs with diverse architectures.

This paper provides a comprehensive overview of CNNs and their applications in image recognition tasks, and reviews recent developments in CNNs, including attention mechanisms, capsule networks, transfer learning, adversarial training, quantization and compression, and enhancing the reliability and efficiency ofCNNs through formal methods.

A survey of security issues in WSNs is presented, the state of the art in research on sensor network security is addressed, and some future directions for research are discussed.

In-network machine learning can significantly benefit cloud computing and next-generation networks, and this survey concludes with a discussion of future trends.

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.

This work introduces a new version of the neural operators called DeepOKAN, which utilizes Kolmogorov Arnold networks (KANs) rather than the conventional neural network architectures, and uses Gaussian radial basis functions (RBFs) rather than the B-splines.

Inductive biases are any assumptions that learners utilize to learn the world and predict the output that reduce the amount of data needed to fit the model while constraining the model’s flexibility.

An overview of the network coding techniques used in wireless networks and evaluates them in terms of latency, reliability and throughput is provided.

A key finding is that the quality of a network for filtering is distinct from its performance on downstream tasks: for instance, a model that performs well on ImageNet can yield worse training sets than a model with low ImageNet accuracy that is trained on a small amount of high-quality data.

An integrated approach combining computer networks and artificial neural networks to construct an intelligent network operator, functioning as an AI model, achieving a 100% accuracy rate and eliminating operational risks is proposed.

This course covers information theory as it relates to networked communication systems, including noiseless network coding, and the impact of eavesdropping and adversarial attacks.

The architecture of optical satellite networks at 100G-1Tbps is explored to architect the system and the network protocols with large bandwidth-delay products and the presence of atmospheric turbulence and weather.

This paper proposes a gradient-based filter insertion scheme to insert interference filters into the important positions in the secret DNN model to form a stego DNNmodel, which is embedded into the stega DNN models using a key by side information hiding.

This paper presents a new deep residual network in network (DrNIN) model that represents a deeper model of DNIN and explicitly reformulate convolutional layers as residual learning functions to solve the vanishing gradient problem and facilitate and speed up the learning process.

This paper proposed an intelligent network management automation algorithm for network administration and management in 5G communication networks that achieved 91.82% of remote network administration, 95.25% of global networkAdministration, 96.59% of urban network management, and 95.07% of local network administration.

Experiments show that KAN Convolutions seem to learn more per kernel, which opens up a new horizon of possibilities in deep learning for computer vision.

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.

A detailed survey of how the IBN concept works and what are the main components to guarantee a fully autonomous IBN system (IBNS), with particular emphasis on the intent expression, intent translation, intent resolution, intent activation and intent assurance components, which form the closed loop automation system of an IBNS.

It is shown that existing NLP-based optimization attacks are insufficiently powerful to reliably attack aligned text models: even when current NLP-based attacks fail, the authors can find adversarial inputs with brute force.

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.

Focal modulation networks (FocalNets in short), where self-attention is completely replaced by a focal modulation mechanism for modeling token interactions in vision, exhibit clear superiority on the tasks of image classification, object detection, and segmentation.

Abstract During a crisis, manufacturing processes in supply chains of different industries may network with each other as an adaptation response. We propose and examine a “network-of-networks” mechanism of such a cross-industry adaptation to learn about the value of reducing uncertainty through collaborative crisis preparedness and response during the COVID-19 pandemic. Our study allows revelation of the underlying trade-offs between the manufacturing capacity conversion time and effort required to adapt and the gains from collaborative preparedness to uncertainty. Through a real-life data-bas...

The key idea of ConWeave is that with the right design, it is possible to perform fine granularity rerouting and mask the effect of out-of-order packet arrivals transparently in the network datapath using a programmable switch.

Experimental results show that the numbers of users served by UAVs in the solutions delivered by the proposed algorithms are increased by 25% than state-of-the-arts.

This work is concerned with simulating heterogeneous contact structures and understanding how the structure of the underlying network affects the spread of the disease.

Inspired by recent developments in vision transformers, VTN is presented, a transformer-based framework for video recognition that enables whole video analysis, via a single end-to-end pass, while requiring 1.5× fewer GFLOPs.

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.

It is demonstrated that gradual magnitude pruning enables value-based agents to maximize parameter effectiveness, resulting in networks that yield dramatic performance improvements over traditional networks, using only a small fraction of the full network parameters.

This study proposes two approaches to speed up Transformer models, where the self-attention mechanism’s quadratic complexity is reduced to linear, enhancing the model’s internal processing speed and creating an efficient attention mechanism.

This work designs a new sampling method, namely random walk with flying-back (RWFB), to conduct effective data sampling and conducts a comprehensive analysis of the Bitcoin network in terms of the degree distribution, clustering coefficient, the shortest-path length, connected component, centrality, assortativity, and the rich-club coefficient.

Forecasting of analyst detection of cyber events is presented as a final method for future anomaly prediction in 5G and outperformed with respect to the KNN and K-prototype methods.

The definition of over-smoothing is axiomatically defined as the exponential convergence of suitable similarity measures on the node features of graph neural networks and extended to the rapidly emerging field of continuous-time GNNs.

This paper designs an encoder to obtain graph embedding, that introduces the graph attention mechanism and considers the edge information as the only essential factor, and proposes a self-supervised method based on graph contrastive learning, the first GNN-based self-supervised method for the multiclass classification of network flows in NIDS.

This article aims to depict the roadmap to the Metaverse in terms of communication and networking in 6G, including illustrating the framework of theMetaverse, revealing the strict requirements and challenges for 6G to realize the MetaVERSE, and discussing the fundamental technologies to be integrated in6G to drive the implementation of the metaverse.

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.

This abstract delves into the various techniques employed by NIDS, ranging from signature-based detection to anomaly detection, and highlights the importance of real-time monitoring and analysis for timely threat detection and response.