Deep Graph-Convolutional Generative Adversarial Network for Semi-Supervised Learning on Graphs

Abstract

Graph convolutional networks (GCNs) are neural network frameworks for machine learning on graphs. They can simultaneously perform end-to-end learning on the attribute information and the structure information of graph data. However, most existing GCNs inevitably encounter the limitations of non-robustness and low classification accuracy when labeled nodes are scarce. To address the two issues, the deep graph convolutional generative adversarial network (DGCGAN), a model combining GCN and deep convolutional generative adversarial networks (DCGAN), is proposed in this paper. First, the graph data is mapped to a highly nonlinear space by using the topology and attribute information of the graph for symmetric normalized Laplacian transform. Then, through the feature-structured enhanced module, the node features are expanded into regular structured data, such as images and sequences, which are input to DGCGAN as positive samples, thus expanding the sample capacity. In addition, the feature-enhanced (FE) module is adopted to enhance the typicality and discriminability of node features, and to obtain richer and more representative features, which is helpful for facilitating accurate classification. Finally, additional constraints are added to the network model by introducing DCGAN, thus enhancing the robustness of the model. Through extensive empirical studies on several standard benchmarks, we find that DGCGAN outperforms state-of-the-art baselines on semi-supervised node classification and remote sensing image classification.

An Efficient Graph Convolutional RVFL Network for Hyperspectral Image Classification

“…Early HSI classification methods such as support vector machine (SVM) [4] focus on either handcrafted shallow-level features or linear separable problems, usually leading to poor robustness. Recently, representation learning centralized by deep neural networks (DNN) has garnered great success in the remote sensing community [5][6][7]. In particular, convolutional neural networks (CNN) [8] have become one of the most representative learning paradigms for HSI classification and building extraction [9,10] due to their powerful ability to automatically extract spectral and spatial information.…”

An Adaptive Enhancement Method of Malicious Traffic Samples Based on DCGAN-ResNet System

“…The device adopts a data-adaptive enhancement method based on deep convolutional generative adversarial networks (DCGAN) to address the imbalance between attack samples and normal samples, improving the overall accuracy of detection models within monitoring systems. Furthermore, the DCGAN, based on generative adversarial network (GAN) (Ring et al, 2019;Kawai et al, 2019;Hu & Tan, 2017;Frid-Adar et al, 2018), introduces convolutional layers to enhance the quality of generated traffic and the training stability of the network (Jia et al, 2023). Through an automated parameter determination method, it further enhances the ability of various system models to detect unknown threats, strengthening the robustness of the model (Tang et al, 2023).…”