Structure-Preserving Graph Representation Learning
This work addresses the problem of incomplete structure embedding in graph representation learning for researchers and practitioners, offering an incremental improvement over existing methods.
The authors tackled the challenge of fully capturing both local and global topological structure in graph representation learning by proposing SPGRL, which constructs a feature graph for local contrast and maximizes mutual information for global structure retention, achieving superior performance in semi-supervised node classification and robustness under noise.
Though graph representation learning (GRL) has made significant progress, it is still a challenge to extract and embed the rich topological structure and feature information in an adequate way. Most existing methods focus on local structure and fail to fully incorporate the global topological structure. To this end, we propose a novel Structure-Preserving Graph Representation Learning (SPGRL) method, to fully capture the structure information of graphs. Specifically, to reduce the uncertainty and misinformation of the original graph, we construct a feature graph as a complementary view via k-Nearest Neighbor method. The feature graph can be used to contrast at node-level to capture the local relation. Besides, we retain the global topological structure information by maximizing the mutual information (MI) of the whole graph and feature embeddings, which is theoretically reduced to exchanging the feature embeddings of the feature and the original graphs to reconstruct themselves. Extensive experiments show that our method has quite superior performance on semi-supervised node classification task and excellent robustness under noise perturbation on graph structure or node features.