Unsupervised Multi-view Nonlinear Graph Embedding

ei, 1 xi, 1 In this paper, we study the unsupervised multi-view graph embedding (UMGE) problem, which aims to learn graph embedding from multiple perspectives in an unsupervised manner. However, the vast majority of multiview learning work focuses on non-graph data, and surprisingly there are limited work on UMGE. By systematically analyzing different existing methods for UMGE, we discover that cross-view and nonlinearity play a vital role in efficiently improving graph embedding quality. Motivated by this concept, we develop an unsupervised Multi-viEw nonlineaR Graph Embedding (MERGE) approach to model relational multi-view consistency. Experimental results on five benchmark datasets demonstrate that MERGE significantly outperforms the state-of-the-art baselines in terms of accuracy in node classification tasks without sacrificing the computational efficiency.

Authors

• Jiaming Huang
• Zhao Li 0007
• Vincent W. Zheng
• Wen Wen
• Yifan Yang 0001
• Yuanmi Chen

Keywords

No keywords are indexed for this paper.