Unsupervised Multiplex Graph Learning with Complementary and Consistent Information
This work addresses practical challenges in graph learning for applications like network analysis, but it appears incremental as it builds on existing UMGL approaches.
The paper tackles the out-of-sample and noise issues in unsupervised multiplex graph learning by proposing a method that uses MLP encoders with constraints for local structure preservation and correlation maximization, achieving superior effectiveness and efficiency over comparison methods.
Unsupervised multiplex graph learning (UMGL) has been shown to achieve significant effectiveness for different downstream tasks by exploring both complementary information and consistent information among multiple graphs. However, previous methods usually overlook the issues in practical applications, i.e., the out-of-sample issue and the noise issue. To address the above issues, in this paper, we propose an effective and efficient UMGL method to explore both complementary and consistent information. To do this, our method employs multiple MLP encoders rather than graph convolutional network (GCN) to conduct representation learning with two constraints, i.e., preserving the local graph structure among nodes to handle the out-of-sample issue, and maximizing the correlation of multiple node representations to handle the noise issue. Comprehensive experiments demonstrate that our proposed method achieves superior effectiveness and efficiency over the comparison methods and effectively tackles those two issues. Code is available at https://github.com/LarryUESTC/CoCoMG.