Multi-Relation Extraction via A Global-Local Graph Convolutional Network

Cheng, Harry H.; Liao, Lizi; Hu, Linmei; Nie, Liqiang

doi:10.1109/tbdata.2022.3144151

Cited by 1 publication

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, when the above models and most GNNs [17][18][19][26][27][28][29] perform semisupervised classification tasks, the accuracy cannot be improved due to the fewer number of samples, and the model lacks robustness. In order to address the two problems, we propose a model named deep graph convolutional generative adversarial networks (DGC-GAN) that integrates DCGAN with GCN.…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2023

View full text Add to dashboard Cite

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.

show abstract