Gated residual recurrent graph neural networks for traffic prediction. Resource Allocation (A GNN-Based Federated Learning Framework for Resource Allocation in Wireless IoT Networks) A GNN-Based Federated Learning Framework for Resource Allocation in Wireless IoT Networks 借助于图的建模,无线物联网系统由图...
Dong G, Tang M, Wang Z, Gao J, Guo S, Cai L, Gutierrez R, Campbel B, Barnes LE, Boukhechba M (2023) Graph neural networks in IoT: a survey. ACM Trans Sensor Netw 19(2):1–50. https://doi.org/10.1145/3565973 Article Google Scholar Zhang S, Tong H, Xu J, Maciejewski R...
This paper introduces a novel IoT Network Intrusion Detection System (NIDS) based on Graph Neural Networks (GNNs). GNNs leverage the topological structure of graph-based data to build correlations between traffic flows. The data can be represented in a flow-based form, where such data can ...
The existing neural networks (Convolutional Neural Networks (CNNs) [1], Recurrent Neural Networks (RNNs) [2], etc.) have been devoted to different problem domains (IoT, etc.), supporting a variety of tasks (prediction, classification, identification, tracking, codesign, and data generation, ...
IoT systems offer a limit to these characteristics. Until recently and to the best of our knowledge, no clear model has been laid out to determine the optimal threshold and trade-off of accuracy and implementation needs of IDS for resource constraint devices. Graph Neural Network (GNN) is a ...
Deep learning Encrypted traffic classification Graph neural networks Attention mechanism 1. Introduction With the rapid development of computer communication and Internet of Things (IoT) technologies, the demand for data security and privacy protection has reached a new level. According to the Google Tran...
Networks(GCN) [30], Graph Attention Networks(GAT) [31], GraphSAGE [32], etc. The early graph neural network algorithm can only deal with static graphs, while the large amount of data faced in daily life often includes an important dimension - time. Spatio-temporal data [33] is a very ...
Chapters 1 and 2 introduced general concepts in machine learning, such asThe different phases that compose a generic machine learning project (specifically, the six phases of the CRISP-DM model: business understanding, data understanding, data preparation, modeling, evaluation, and deployment) The ...
The introduction of Graph Neural Networks (GNNs) brings forth a transformative solution, particularly in their ability to capture high-order dependencies between POIs, understanding deeper relationships and patterns beyond immediate connections. This survey presents a comprehensive exploration of GNN-based ...
Next, in contrast to expensive dual [6], [11] or triplet [19] self-supervision, SCGC is able to use a simpler single (self) supervision. Then, unlike other models that use a combination of auto encoders (AE) and Graph Convolution networks (GCN, IGAE), SCGC uses a simple encoder (...