Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence

Abstract

Convolutional neural networks (CNNs) have received widespread attention due to their powerful modeling capabilities and have been successfully applied in natural language processing, image recognition, and other fields. On the other hand, traditional CNN can only deal with Euclidean spatial data. In contrast, many real-life scenarios, such as transportation networks, social networks, reference networks, and so on, exist in graph data. The creation of graph convolution operators and graph pooling is at the heart of migrating CNN to graph data analysis and processing. With the advancement of the Internet and technology, graph convolution network (GCN), as an innovative technology in artificial intelligence (AI), has received more and more attention. GCN has been widely used in different fields such as image processing, intelligent recommender system, knowledge-based graph, and other areas due to their excellent characteristics in processing non-European spatial data. At the same time, communication networks have also embraced AI technology in recent years, and AI serves as the brain of the future network and realizes the comprehensive intelligence of the future grid. Many complex communication network problems can be abstracted as graph-based optimization problems and solved by GCN, thus overcoming the limitations of traditional methods. This survey briefly describes the definition of graph-based machine learning, introduces different types of graph networks, summarizes the application of GCN in various research fields, analyzes the research status, and gives the future research direction.

A Super-Efficient GSM Triplexer for 5G-Enabled IoT in Sustainable Smart Grid Edge Computing and the Metaverse

“…It uses advanced metering infrastructure and communication technologies to monitor, manage and respond to unexpected changes in the power grid [ 8 ]. A paper analyzed the research status of AI and provided future research directions [ 9 ]. In addition, a safe decision controller for autonomous driving using deep reinforcement learning in a nondeterministic environment was conducted in another paper [ 10 ].…”

Grasping and cutting points detection method for the harvesting of dome-type planted pumpkin using transformer network-based instance segmentation architecture

“…In recent years, deep learning applications have attracted great attention and made great breakthroughs in image processing tasks (Liu et al, 2021a;Bhatti et al, 2023), the research on learning-based fruit and vegetable detection also moves forward. Liu et al (2019a) trained a Support Vector Machine (SVM) classifier utilizing the Histograms of Oriented Gradients (HOG) descriptor to detect mature tomatoes.…”

“…In recent years, deep learning applications have attracted great attention and made great breakthroughs in image processing tasks ( Liu et al., 2021a ; Bhatti et al., 2023 ), the research on learning-based fruit and vegetable detection also moves forward. Liu et al.…”

Classification method of lithographic layout patterns based on graph convolutional network with graph attention mechanism

“…Thus, compared with the traditional CNNs, GCN has a simpler network structure. 20,21 In addition, GCN limits the number of model parameters by improving and optimizing the propagation function of the graph convolutional layer. 21 Therefore, GCN alleviates the problem of overfitting.…”

“…The GCN usually includes a few convolutional layers because of the over-smoothing problem. Thus, compared with the traditional CNNs, GCN has a simpler network structure 20 , 21 . In addition, GCN limits the number of model parameters by improving and optimizing the propagation function of the graph convolutional layer 21 .…”