On the use of high-order feature propagation in Graph Convolution Networks with Manifold Regularization
Graph Convolutional Networks (GCNs) have received a lot of attention in pattern recognition and machine learning. In this paper, we present a revisited scheme for the new method called "GCNs with Manifold Regularization" (GCNMR). While manifold regularization can add additional information...
| Autor: | |
|---|---|
| Formato: | artículo |
| Fecha de publicación: | 2022 |
| País: | España |
| Recursos: | Universidad del País Vasco |
| Repositorio: | Addi. Archivo Digital para la Docencia y la Investigación |
| OAI Identifier: | oai:addi.ehu.eus:10810/55139 |
| Acesso em linha: | http://hdl.handle.net/10810/55139 |
| Access Level: | acceso abierto |
| Palavra-chave: | graph-based semi-supervised learning graph convolution networks (GCN) graph convolution networks with manifold regularization (GCNMR) feature propagation label prediction manifold regularization semi-supervised image classification |
| Resumo: | Graph Convolutional Networks (GCNs) have received a lot of attention in pattern recognition and machine learning. In this paper, we present a revisited scheme for the new method called "GCNs with Manifold Regularization" (GCNMR). While manifold regularization can add additional information, the GCN-based semi-supervised classification process cannot consider the full layer-wise structured information. Inspired by graph-based label propagation approaches, we will integrate high-order feature propagation into each GCN layer. High-order feature propagation over the graph can fully exploit the structured information provided by the latter at all the GCN's layers. It fully exploits the clustering assumption, which is valid for structured data but not well exploited in GCNs. Our proposed scheme would lead to more informative GCNs. Using the revisited model, we will conduct several semi-supervised classification experiments on public image datasets containing objects, faces and digits: Extended Yale, PF01, Caltech101 and MNIST. We will also consider three citation networks. The proposed scheme performs well compared to several semi-supervised methods. With respect to the recent GCNMR approach, the average improvements were 2.2%, 4.5%, 1.0% and 10.6% on Extended Yale, PF01, Caltech101 and MNIST, respectively. |
|---|