Data Representation and Learning With Graph Diffusion-Embedding Networks
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 10406-10415
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.Keywords
This publication has 13 references indexed in Scilit:
- Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs2017
- DeepWalk2014
- Diffusion Processes for Retrieval Revisited2013
- Graph-Laplacian PCA: Closed-Form Solution and Robustness2013
- Multiview Spectral EmbeddingIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2010
- The Graph Neural Network ModelIEEE Transactions on Neural Networks, 2008
- Collective Classification in Network DataAI Magazine, 2008
- A new model for learning in graph domains2006
- A general framework for adaptive processing of data structuresIEEE Transactions on Neural Networks, 1998
- Supervised neural networks for the classification of structuresIEEE Transactions on Neural Networks, 1997