Data Representation and Learning With Graph Diffusion-Embedding Networks

Bo Jiang, Doudou Lin, Jin Tang, Bin Luo; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 10414-10423

Abstract


Recently, graph convolutional neural networks have been widely studied for graph-structured data representation and learning. In this paper, we present Graph Diffusion-Embedding networks (GDENs), a new model for graph-structured data representation and learning. GDENs are motivated by our development of graph based feature diffusion. GDENs integrate both feature diffusion and graph node (low-dimensional) embedding simultaneously into a unified network by employing a novel diffusion-embedding architecture. GDENs have two main advantages. First, the equilibrium representation of the diffusion-embedding operation in GDENs can be obtained via a simple closed-form solution, which thus guarantees the compactivity and efficiency of GDENs. Second, the proposed GDENs can be naturally extended to address the data with multiple graph structures. Experiments on various semi-supervised learning tasks on several benchmark datasets demonstrate that the proposed GDENs significantly outperform traditional graph convolutional networks.

Related Material


[pdf]
[bibtex]
@InProceedings{Jiang_2019_CVPR,
author = {Jiang, Bo and Lin, Doudou and Tang, Jin and Luo, Bin},
title = {Data Representation and Learning With Graph Diffusion-Embedding Networks},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}