PCANE: Preserving Context Attributes for Network Embedding

Zhu, Danhao; Dai, Xinyu; Yang, Kaijia; Chen, Jiajun; He, Yong

doi:10.1007/978-3-030-16142-2_13

Cited by 2 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhu et al [12] proposed an unsupervised graph learning method that utilizes the context attributes. The node representations are learned by jointly optimizing two objective functions that preserve the neighborhood nodes and attributes.…”

Section: Global Attribute Featuresmentioning

confidence: 99%

Pre-Train and Learn: Preserving Global Information for Graph Neural Networks

Zhu

Dai

Chen

2021

J. Comput. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Graph neural networks (GNNs) have shown great power in learning on graphs. However, it is still a challenge for GNNs to model information faraway from the source node. The ability to preserve global information can enhance graph representation and hence improve classification precision. In the paper, we propose a new learning framework named G-GNN (Global information for GNN) to address the challenge. First, the global structure and global attribute features of each node are obtained via unsupervised pre-training, and those global features preserve the global information associated with the node. Then, using the pre-trained global features and the raw attributes of the graph, a set of parallel kernel GNNs is used to learn different aspects from these heterogeneous features. Any general GNN can be used as a kernal and easily obtain the ability of preserving global information, without having to alter their own algorithms. Extensive experiments have shown that state-of-the-art models, e.g., GCN, GAT, Graphsage and APPNP, can achieve improvement with G-GNN on three standard evaluation datasets. Specially, we establish new benchmark precision records on Cora (84.31%) and Pubmed (80.95%) when learning on attributed graphs.

show abstract

Section: Global Attribute Featuresmentioning

confidence: 99%

Pre-Train and Learn: Preserving Global Information for Graph Neural Networks

Zhu

Dai

Chen

2021

J. Comput. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Attributed Graph Embedding: Recent studies [1,7,8,11,15,19,21] show that the incorporation of node attributes along with graph structure produces better node embeddings. TADW [19] incorporates text attributes and graph structure with low-rank matrix factorization.…”

Section: Related Workmentioning

confidence: 99%

“…Most existing graph embedding methods learn node embeddings from graph topological structure only [6,13,16,17]. However, nodes in a graph usually have supplementary attribute information which can be utilized in graph embedding along with the graph structure to produce more meaningful node embeddings [7,11,15,21].…”

Section: Introductionmentioning

confidence: 99%

Robust Attribute and Structure Preserving Graph Embedding

Hettige

Wang

et al. 2020

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Graph embedding methods are useful for a wide range of graph analysis tasks including link prediction and node classification. Most graph embedding methods learn only the topological structure of graphs. Nevertheless, it has been shown that the incorporation of node attributes is beneficial in improving the expressive power of node embeddings. However, real-world graphs are often noisy in terms of structure and/or attributes (missing and/or erroneous edges/attributes). Most existing graph embedding methods are susceptible to this noise, as they do not consider uncertainty during the modelling process. In this paper, we introduce RASE, a Robust Attribute and Structure preserving graph Embedding model. RASE is a novel graph representation learning model which effectively preserves both graph structure and node attributes through a unified loss function. To be robust, RASE uses a denoising attribute auto-encoder to deal with node attribute noise, and models uncertainty in the embedding space as Gaussians to cope with graph structure noise. We evaluate the performance of RASE through an extensive experimental study on various real-world datasets. Results demonstrate that RASE outperforms state-of-the-art embedding methods on multiple graph analysis tasks and is robust to both structure and attribute noise.

show abstract

PCANE: Preserving Context Attributes for Network Embedding

Cited by 2 publications

References 12 publications

Pre-Train and Learn: Preserving Global Information for Graph Neural Networks

Pre-Train and Learn: Preserving Global Information for Graph Neural Networks

Robust Attribute and Structure Preserving Graph Embedding

Contact Info

Product

Resources

About